© 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. 85316
    Prev
    Next
    INDEX
    Explanations

    No pattern was found.CL

    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
    方言
    -0.07
     feedback
    -0.07
    _iface
    -0.07
    �试
    -0.07
     Esper
    -0.07
    してください
    -0.07
    𝔰
    -0.06
    躞
    -0.06
    ጽ
    -0.06
    phas
    -0.06
    POSITIVE LOGITS
     PackageManager
    0.08
    JS
    0.07
    Engine
    0.07
    FULL
    0.07
    ,null
    0.06
     reputation
    0.06
    GL
    0.06
    Pre
    0.06
     Liste
    0.06
     pen
    0.06
    Activations Density 0.038%

    No Known Activations