© 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. 11524
    Prev
    Next
    INDEX
    Explanations

    places and names

    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
    chest
    -0.09
    é«ĺæĺĤ
    -0.09
    ä¸Ģ对
    -0.09
    åİ»åģļ
    -0.09
    åģĩè£ħ
    -0.09
    _INTR
    -0.09
     zakÅĤad
    -0.09
    åĽ¢
    -0.09
    ITCH
    -0.09
    æĨ
    -0.09
    POSITIVE LOGITS
    å½ĵåľ°æŶéĹ´
    0.09
    æĸ½çŃĸ
    0.08
     aug
    0.08
    å¯ĴåĨ¬
    0.08
     legend
    0.08
     avid
    0.08
    -esque
    0.07
    æĻļæľŁ
    0.07
    utsch
    0.07
    Tes
    0.07
    Activations Density 0.290%

    No Known Activations