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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 86557
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    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
     destino
    -0.08
    ennai
    -0.07
    羸
    -0.06
    ☐
    -0.06
    ച
    -0.06
     UIEdgeInsets
    -0.06
    akistan
    -0.06
    Tv
    -0.06
    redni
    -0.06
    Marg
    -0.06
    POSITIVE LOGITS
    مباد
    0.08
    (list
    0.07
     htmlspecialchars
    0.07
    Layer
    0.07
    .shape
    0.07
    .lt
    0.07
     Viktor
    0.07
     alters
    0.07
    ALTER
    0.07
     fundamentally
    0.07
    Activations Density 0.006%

    No Known Activations