Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 71838
    Prev
    Next
    INDEX
    Explanations

    ologic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cesso
    -0.08
    公民
    -0.07
    .localized
    -0.07
     jeżeli
    -0.07
    在哪
    -0.07
    多余
    -0.07
    .constraints
    -0.06
     nail
    -0.06
     quali
    -0.06
     fatally
    -0.06
    POSITIVE LOGITS
    cut
    0.07
    🌿
    0.07
    ילות
    0.07
    Focus
    0.06
    Rot
    0.06
    UCCEEDED
    0.06
    AIT
    0.06
     old
    0.06
    .Width
    0.06
     Mining
    0.06
    Activations Density 0.106%

    No Known Activations