© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 11145
    Prev
    Next
    INDEX
    Explanations

    FBI

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atta
    -0.07
     Unsafe
    -0.07
    냐
    -0.07
    atas
    -0.07
    WORK
    -0.06
    Chat
    -0.06
    coupon
    -0.06
    嫩
    -0.06
    ymous
    -0.06
    nty
    -0.06
    POSITIVE LOGITS
    的能量
    0.09
    (Target
    0.08
    殖民
    0.08
    _stage
    0.07
     yönt
    0.07
    その後
    0.07
    🤍
    0.07
     itemCount
    0.07
    重启
    0.07
    𝘰
    0.07
    Activations Density 0.002%

    No Known Activations