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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24407
    Prev
    Next
    INDEX
    Explanations

    view

    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
    .Toolbar
    -0.08
    (pwd
    -0.07
    (profile
    -0.07
    -marker
    -0.07
    (tbl
    -0.07
     traumatic
    -0.07
     TOUR
    -0.07
     André
    -0.07
    _REST
    -0.07
    Themes
    -0.07
    POSITIVE LOGITS
    长沙市
    0.07
    是一款
    0.06
    ائح
    0.06
    /O
    0.06
     schematic
    0.06
    fight
    0.06
     Animated
    0.06
    نشاط
    0.06
    気持ち
    0.06
    ification
    0.06
    Activations Density 0.008%

    No Known Activations