© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63207
    Prev
    Next
    INDEX
    Explanations

    pistol or handgun

    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
    rise
    -0.11
    女ç¥ŀ
    -0.09
    же
    -0.09
    èĢģ人家
    -0.09
    istory
    -0.09
    thew
    -0.09
    æºľ
    -0.09
    åľĥ
    -0.08
    çĶŁäº§æĢ»åĢ¼
    -0.08
    lus
    -0.08
    POSITIVE LOGITS
    çķĪ
    0.10
    ke
    0.09
    ../../../
    0.09
    _SCR
    0.09
    eros
    0.08
    åħļé£İ
    0.08
    æĺ¼å¤ľ
    0.08
    bitset
    0.08
    丸
    0.08
     dạ
    0.08
    Activations Density 0.009%

    No Known Activations