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. 88302
    Prev
    Next
    INDEX
    Explanations

    \_

    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
    烹
    -0.08
    Mc
    -0.07
    StringEncoding
    -0.07
     rect
    -0.07
    _TRANSACTION
    -0.07
    .Fatal
    -0.07
    ****************************************************************
    -0.07
    至关重要
    -0.07
     Cascade
    -0.07
     Prelude
    -0.07
    POSITIVE LOGITS
     showed
    0.07
    Ժ
    0.07
    雪
    0.06
     компаний
    0.06
    貸款
    0.06
     earned
    0.06
    ᅭ
    0.06
     petites
    0.06
     kleinen
    0.06
     contraction
    0.06
    Activations Density 0.007%

    No Known Activations