© 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. 40028
    Prev
    Next
    INDEX
    Explanations

    Drugs

    np_max-act · gemini-2.0-flash

    mentions of secretly lacing or drugging drinks/food (e.g., aphrodisiacs, sedatives, poison) and their effects on the victim

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    ART
    -0.07
    毁
    -0.07
     rehe
    -0.06
     대통령
    -0.06
     OFF
    -0.06
    ‐
    -0.06
     municipality
    -0.06
    𝛼
    -0.06
    /ref
    -0.06
    落实
    -0.06
    POSITIVE LOGITS
     erh
    0.08
    쌨
    0.08
     strongest
    0.07
    хи
    0.07
    ╋
    0.07
     пока
    0.07
    ขาว
    0.07
    explain
    0.07
     besoin
    0.07
    こんに
    0.07
    Activations Density 0.049%

    No Known Activations