© 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. 15-RESID-POST-AA
    11. 116833
    Prev
    Next
    INDEX
    Explanations

    jury

    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
    olumes
    -0.07
    也有一些
    -0.07
    信息系统
    -0.07
    locales
    -0.06
    Levels
    -0.06
    &a
    -0.06
    UNCTION
    -0.06
     irre
    -0.06
    عجز
    -0.06
    还真
    -0.06
    POSITIVE LOGITS
     Kami
    0.07
    唐宇
    0.06
    堽
    0.06
    标记
    0.06
     kształ
    0.06
    믹
    0.06
     Export
    0.06
    _OC
    0.06
    מבנה
    0.06
    wing
    0.06
    Activations Density 0.000%

    No Known Activations