© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 116110
    Prev
    Next
    INDEX
    Explanations

    Impersonation

    np_max-act · gemini-2.0-flash

    descriptions of deception and impersonation—people adopting false identities, disguises, or cover stories to appear as something they’re not.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sufficiently
    -0.07
    компонент
    -0.07
     calculator
    -0.07
     revolutionary
    -0.07
     indexOf
    -0.07
    醫生
    -0.07
     %[
    -0.07
     sufficient
    -0.07
     accomplish
    -0.07
    ders
    -0.07
    POSITIVE LOGITS
    .nom
    0.07
    룐
    0.07
    essoa
    0.07
    𝒟
    0.07
    wa
    0.06
    午后
    0.06
    Opacity
    0.06
    ㎑
    0.06
     günl
    0.06
    න
    0.06
    Activations Density 0.062%

    No Known Activations