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. 7286
    Prev
    Next
    INDEX
    Explanations

    device

    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
    煳
    -0.07
    //↵↵↵
    -0.07
    .basic
    -0.07
     seaside
    -0.07
    atial
    -0.07
    _Desc
    -0.06
     Cabin
    -0.06
    academic
    -0.06
    脑子里
    -0.06
    clientId
    -0.06
    POSITIVE LOGITS
     franchises
    0.08
     организация
    0.07
    的价格
    0.07
     captivating
    0.07
     maiden
    0.07
    fung
    0.07
    (block
    0.07
    ufacturer
    0.07
    车辆
    0.07
    rices
    0.07
    Activations Density 0.003%

    No Known Activations