© 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. 83348
    Prev
    Next
    INDEX
    Explanations

    recipes

    np_max-act · gemini-2.0-flash

    Text about cooking — recipes, ingredients, measurements, and step-by-step cooking instructions.

    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
    GINE
    -0.08
     Anton
    -0.07
     ללא
    -0.06
    HRESULT
    -0.06
    .]
    -0.06
    ᠂
    -0.06
     규
    -0.06
     Whale
    -0.06
    一处
    -0.06
    本来就
    -0.06
    POSITIVE LOGITS
    -provider
    0.07
     отправ
    0.07
    еб
    0.07
    _NB
    0.07
    _startup
    0.06
    俦
    0.06
    ław
    0.06
     rd
    0.06
    喃
    0.06
     our
    0.06
    Activations Density 1.067%

    No Known Activations