© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60927
    Prev
    Next
    INDEX
    Explanations

    Boston

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å©¿
    -0.09
    inary
    -0.09
    ppard
    -0.08
    åŀĽ
    -0.08
    utz
    -0.08
    éªĸ
    -0.08
    ../../../
    -0.08
    æ±Łåİ¿
    -0.08
    綦
    -0.08
     Zimmer
    -0.08
    POSITIVE LOGITS
    ized
    0.11
    sek
    0.11
    -fw
    0.10
    ogle
    0.10
     thiá»ĥu
    0.10
    ìį¨
    0.10
    ised
    0.09
     Fairfax
    0.09
    éķ°
    0.09
    izador
    0.09
    Activations Density 0.010%

    No Known Activations