© 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. 85941
    Prev
    Next
    INDEX
    Explanations

    https

    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
    完备
    -0.07
    lightly
    -0.07
     submissions
    -0.07
    conti
    -0.07
    恶性
    -0.06
    敢
    -0.06
    .environ
    -0.06
    null
    -0.06
    _fin
    -0.06
    *S
    -0.06
    POSITIVE LOGITS
    isecond
    0.08
     ql
    0.07
    ظام
    0.07
    鄉
    0.07
    arsers
    0.06
    Alter
    0.06
    冻结
    0.06
     ActiveForm
    0.06
     Tablets
    0.06
     SharePoint
    0.06
    Activations Density 0.001%

    No Known Activations