© 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. 946
    Prev
    Next
    INDEX
    Explanations

    Sports teams and names

    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
    éĻŁ
    -0.11
    ingly
    -0.10
    èĻŀ
    -0.10
    busters
    -0.09
    _Reg
    -0.09
    躬
    -0.09
    éģ½
    -0.09
     antid
    -0.09
    orary
    -0.08
    ´
    -0.08
    POSITIVE LOGITS
    igor
    0.09
    âķĹ
    0.09
    oris
    0.09
    Ñĩе
    0.09
    amed
    0.08
    åĿŀ
    0.08
    主ä¹īæĢĿæĥ³
    0.08
    flare
    0.08
     MX
    0.08
    oxy
    0.08
    Activations Density 0.010%

    No Known Activations