© 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. 15-RESID-POST-AA
    11. 5716
    Prev
    Next
    INDEX
    Explanations

    G

    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
    Negative Logits
     vibrations
    -0.08
    厦门
    -0.07
    czas
    -0.07
    	com
    -0.07
    这是我们
    -0.07
    各位
    -0.07
     incidence
    -0.07
    _em
    -0.07
    úng
    -0.06
    Congratulations
    -0.06
    POSITIVE LOGITS
    -sur
    0.08
     Mult
    0.08
    Culture
    0.07
    ไต
    0.07
    缛
    0.07
    >$
    0.07
     CPPUNIT
    0.07
     roy
    0.07
    裤
    0.07
    تحر
    0.07
    Activations Density 0.082%

    No Known Activations