© 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. 84845
    Prev
    Next
    INDEX
    Explanations

    User reviews/comments

    np_max-act · gemini-2.0-flash

    sentimentally intense negative or hostile user language (insults, outrage, strong complaints/exasperation).

    oai_token-act-pair · gpt-5-miniTriggered 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
    /auto
    -0.08
    ный
    -0.07
     литератур
    -0.07
     nano
    -0.07
    上百
    -0.07
    г
    -0.07
     homemade
    -0.07
     tbsp
    -0.07
    فئة
    -0.06
    ڿ
    -0.06
    POSITIVE LOGITS
    鹀
    0.07
    vat
    0.07
     contract
    0.07
    徛
    0.06
    .rotation
    0.06
    揸
    0.06
    文化建设
    0.06
    Strategy
    0.06
    ___↵↵
    0.06
    (dx
    0.06
    Activations Density 0.070%

    No Known Activations