© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 5848
    Prev
    Next
    INDEX
    Explanations

    Online forum discussions

    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
    香水
    -0.07
    Replace
    -0.07
    服务中心
    -0.07
    每一天
    -0.07
    水量
    -0.07
     wikipedia
    -0.06
    쌜
    -0.06
     ?><?
    -0.06
     Replace
    -0.06
     Doors
    -0.06
    POSITIVE LOGITS
     tek
    0.07
     motors
    0.07
    _tele
    0.07
    经纬
    0.07
    盡
    0.07
     lucky
    0.06
    جب
    0.06
    宝贝
    0.06
    constructed
    0.06
     regulated
    0.06
    Activations Density 0.053%

    No Known Activations