© 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. 3040
    Prev
    Next
    INDEX
    Explanations

    furious, fury, infuriating, ferocious

    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
    åĢĮ
    -0.10
     Guerr
    -0.10
    orc
    -0.09
    omination
    -0.09
    ä¾£
    -0.08
    fell
    -0.08
    æĥħæĢĢ
    -0.08
    è´¢
    -0.08
    alog
    -0.08
    æĶ¾çľ¼
    -0.08
    POSITIVE LOGITS
    usra
    0.10
    ity
    0.10
    lic
    0.10
    enco
    0.10
    ITY
    0.09
    说æĺ¯
    0.09
    icates
    0.09
    naire
    0.09
    iler
    0.09
    åľ°å¸¦
    0.09
    Activations Density 0.002%

    No Known Activations