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. 87773
    Prev
    Next
    INDEX
    Explanations

    rate

    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
     Тур
    -0.07
     strife
    -0.07
    评估
    -0.07
    انية
    -0.07
    𝑖
    -0.07
    ング
    -0.07
    封闭
    -0.07
     east
    -0.07
     Brah
    -0.07
     Lon
    -0.07
    POSITIVE LOGITS
     ten
    0.07
    citation
    0.07
    彪
    0.07
    号码
    0.07
    หมวด
    0.07
    统
    0.07
    .tokenize
    0.07
    .XtraPrinting
    0.07
    取
    0.06
    京城
    0.06
    Activations Density 0.433%

    No Known Activations