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. 2907
    Prev
    Next
    INDEX
    Explanations

    say capital letter word

    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
    :number
    -0.07
    宝妈
    -0.07
     يجب
    -0.07
    (JSON
    -0.07
     siendo
    -0.07
     Wochen
    -0.06
    .DELETE
    -0.06
     Nb
    -0.06
     SOCKET
    -0.06
    $status
    -0.06
    POSITIVE LOGITS
    ፈ
    0.07
    relay
    0.07
    etto
    0.07
     splash
    0.07
    .fml
    0.07
     walks
    0.07
    _cpp
    0.07
    basePath
    0.07
    chied
    0.07
    メー�
    0.07
    Activations Density 0.023%

    No Known Activations