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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52292
    Prev
    Next
    INDEX
    Explanations

    sweat and related conditions

    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
    eness
    -0.11
    æ¸IJ
    -0.10
    OND
    -0.10
    led
    -0.09
    ity
    -0.09
    ocab
    -0.09
    éļ§
    -0.08
     jewish
    -0.08
    ets
    -0.08
    ptime
    -0.08
    POSITIVE LOGITS
    alo
    0.11
    è¤Ł
    0.10
    æĨ©
    0.10
    tractor
    0.10
    chez
    0.09
    gin
    0.09
    .RESET
    0.09
    æģĥ
    0.09
    _LOOKUP
    0.09
    shirt
    0.08
    Activations Density 0.012%

    No Known Activations