© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 11-RESID-POST-AA
    11. 72144
    Prev
    Next
    INDEX
    Explanations

    itis

    np_max-act · gemini-2.0-flash

    medical and clinical terms, especially cardiac-related conditions, procedures, and adverse events (e.g., QT interval, ventricular arrhythmias, envenomation).

    oai_token-act-pair · gpt-5-mini
    Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    卖场
    -0.06
     mozilla
    -0.06
     {}".
    -0.06
    }".
    -0.06
     widened
    -0.06
    --*/↵
    -0.06
    cosa
    -0.06
    ！！↵↵
    -0.06
     define
    -0.06
    %"↵
    -0.06
    POSITIVE LOGITS
    წ
    0.08
    .firstChild
    0.07
    镗
    0.07
    _POSTFIELDS
    0.07
    无效
    0.07
    .No
    0.07
    .jpa
    0.07
    为止
    0.07
    utherford
    0.07
    路桥
    0.07
    Activations Density 27.868%

    No Known Activations