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. 71236
    Prev
    Next
    INDEX
    Explanations

    love

    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
    ’à
    -0.07
     revive
    -0.07
    {@
    -0.07
    .booking
    -0.07
    =max
    -0.06
    𥖨
    -0.06
     damned
    -0.06
    ’une
    -0.06
    ˔
    -0.06
    <translation
    -0.06
    POSITIVE LOGITS
    技巧
    0.08
     Serbia
    0.08
     Nile
    0.07
    ห
    0.07
     القاهرة
    0.07
     kilometers
    0.07
    usty
    0.07
    _none
    0.06
    淹
    0.06
    (KeyEvent
    0.06
    Activations Density 0.046%

    No Known Activations