© 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. 33479
    Prev
    Next
    INDEX
    Explanations

    whether or not

    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
    大æ¦Ĥæĺ¯
    -0.09
    UCH
    -0.08
    бо
    -0.08
    ãģ§ãģĹãĤĩãģĨãģŃ
    -0.08
     há»ĵi
    -0.08
    ibu
    -0.08
     Rig
    -0.08
    ToF
    -0.08
    uche
    -0.08
    æĻļæľŁ
    -0.08
    POSITIVE LOGITS
    éĴ³
    0.11
    çľ·
    0.10
    éĹªåħī
    0.10
    çIJĨä¼ļ
    0.10
    ÑĥÑĩа
    0.10
    Ops
    0.09
    éĥ½ä¼ļæľī
    0.09
    æµij
    0.09
    åĺ´
    0.09
    ãģªãģıãģ¦ãĤĤ
    0.09
    Activations Density 0.037%

    No Known Activations