© 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. 30244
    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
    azzi
    -0.11
    /inet
    -0.10
    å¸ĥ
    -0.09
    _TYP
    -0.09
    ãģĦãģŁãģł
    -0.09
    å¸Ĥåİ¿
    -0.09
    itat
    -0.08
    éĻ¢
    -0.08
    _MIDDLE
    -0.08
    åħĭæľį
    -0.08
    POSITIVE LOGITS
    缪
    0.08
    太
    0.08
    è¾±
    0.08
     Dix
    0.08
    wig
    0.08
    çĦ¶æĺ¯
    0.08
    vig
    0.08
    erte
    0.08
    ä¸Ĭä¸ĭ
    0.08
     ÑĦÑĥÑĤ
    0.08
    Activations Density 0.003%

    No Known Activations