© 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. 37224
    Prev
    Next
    INDEX
    Explanations

    cytochrome P450

    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
    vern
    -0.10
    igon
    -0.10
    (_.
    -0.09
    anzi
    -0.09
    .Scope
    -0.09
    ÙħÙĬØ©
    -0.09
    ushi
    -0.09
    为ä¹ĭ
    -0.08
    arded
    -0.08
    .places
    -0.08
    POSITIVE LOGITS
    è¹Ī
    0.11
    æķ¢
    0.09
     ju
    0.08
    CHR
    0.08
    ä¸ĢåĽ¢
    0.08
    åĭī
    0.08
    è·µ
    0.08
    磼
    0.08
    çŀ»
    0.08
    ç¿İ
    0.07
    Activations Density 0.050%

    No Known Activations