© 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. 23902
    Prev
    Next
    INDEX
    Explanations

    .Runtime

    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
     getMenuInflater
    -0.07
    牌子
    -0.07
     HMS
    -0.07
    新一代
    -0.07
    ssl
    -0.07
     primer
    -0.07
    CERT
    -0.07
    \"\
    -0.06
    名气
    -0.06
    _SMS
    -0.06
    POSITIVE LOGITS
     năng
    0.08
    どういう
    0.08
    รอบ
    0.07
    patients
    0.07
    OrCreate
    0.07
     persec
    0.07
     sobą
    0.07
     الثال
    0.07
    -client
    0.07
     enchant
    0.07
    Activations Density 0.001%

    No Known Activations