© 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. 57436
    Prev
    Next
    INDEX
    Explanations

    Magnuson-Moss Warranty Act

    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
    inas
    -0.10
    sonian
    -0.09
    ä½ĵ
    -0.09
    ç°ª
    -0.09
    å¿«éĢĴ
    -0.09
    èĥ´
    -0.09
    å¯Ħæīĺ
    -0.09
    IMER
    -0.09
    _$_
    -0.09
    é¢ł
    -0.09
    POSITIVE LOGITS
    OWNER
    0.09
     disg
    0.08
    æ²¹èĢĹ
    0.08
    ä¿Ŀä¿®
    0.08
     Seas
    0.08
    lette
    0.08
    _units
    0.08
    年度
    0.08
    DBG
    0.08
    溢
    0.08
    Activations Density 0.243%

    No Known Activations