© 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. 58786
    Prev
    Next
    INDEX
    Explanations

    give it a go

    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
    éļıä¹ĭ
    -0.10
     Coron
    -0.10
    rough
    -0.09
    æľī大éĩıçļĦ
    -0.08
    让å®ĥ
    -0.08
     Monterey
    -0.08
    urally
    -0.08
    ä¸ĢåĪĩ
    -0.08
    åħ¶å®ĥéĹ®é¢ĺ
    -0.08
    æł¸ç®Ĺ
    -0.08
    POSITIVE LOGITS
    åħ¬æĬ¥
    0.09
    ImageRelation
    0.09
    æĭĪ
    0.09
    æĺŁæĺŁ
    0.09
    æĸ¯åŁº
    0.09
    _abort
    0.09
    ä½ľä¸ºä¸Ģç§į
    0.09
    voke
    0.09
    ega
    0.08
    èĥĿ
    0.08
    Activations Density 0.162%

    No Known Activations