© 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. 1941
    Prev
    Next
    INDEX
    Explanations

    num

    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
    Sport
    -0.08
    _Start
    -0.07
    Mut
    -0.07
    Tpl
    -0.07
    全て
    -0.07
    _vect
    -0.06
     Shop
    -0.06
     Spike
    -0.06
    /P
    -0.06
    崛起
    -0.06
    POSITIVE LOGITS
    תחת
    0.07
     thy
    0.07
     upper
    0.07
    listing
    0.07
     QHBoxLayout
    0.06
    生活质量
    0.06
    ibur
    0.06
    ardon
    0.06
    工作中
    0.06
    ların
    0.06
    Activations Density 0.000%

    No Known Activations