© 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. 42256
    Prev
    Next
    INDEX
    Explanations

    morning/evening

    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
     mez
    -0.07
    /h
    -0.07
    思维方式
    -0.07
    介入
    -0.07
    葸
    -0.06
    /hr
    -0.06
    Appe
    -0.06
    profession
    -0.06
     freel
    -0.06
    镅
    -0.06
    POSITIVE LOGITS
     Reality
    0.07
    locale
    0.07
    _print
    0.07
    oran
    0.06
    _crit
    0.06
     Baltimore
    0.06
    긑
    0.06
    קטגור
    0.06
    臨
    0.06
    libraries
    0.06
    Activations Density 0.009%

    No Known Activations