© 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. 50879
    Prev
    Next
    INDEX
    Explanations

    children and siblings

    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
     Typed
    -0.08
    妯
    -0.08
    å§Ĵ
    -0.08
    iest
    -0.08
    家æĹı
    -0.08
    èµ°åĩºæĿ¥
    -0.08
     Sah
    -0.08
    丰满
    -0.08
    sess
    -0.08
     Sa
    -0.08
    POSITIVE LOGITS
    æĨ§æĨ¬
    0.10
    å»Ľ
    0.10
    à¸Ļà¸Ńà¸ģ
    0.10
    åģ¥åº·æĪIJéķ¿
    0.10
    主è¦ģä»İäºĭ
    0.10
    ikal
    0.09
    æĺ¯éŁ©åĽ½
    0.09
    odal
    0.09
    缮åīįæŃ£åľ¨
    0.09
    éĢļåħ³
    0.09
    Activations Density 0.033%

    No Known Activations