© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19936
    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
    æĭĨ
    -0.12
    izza
    -0.10
    æĭĨéĻ¤
    -0.09
    èģĶåIJĪä¼ļ
    -0.09
    sa
    -0.09
    æķĪæŀľ
    -0.08
    é¢Ħ约
    -0.08
    æµģ泪
    -0.08
    ç¡®
    -0.08
    .Appearance
    -0.08
    POSITIVE LOGITS
    åı±
    0.09
    é«Ģ
    0.09
    å¿«ä¸ī
    0.09
    ä¸įæĺİ
    0.09
    çŃ¹çłģ
    0.08
    河边
    0.08
    æ¯Ľ
    0.08
    çīĪæĿĥå½Ĵ
    0.08
    ä¸į足
    0.08
    æĻĸ
    0.08
    Activations Density 0.001%

    No Known Activations