© 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. 63008
    Prev
    Next
    INDEX
    Explanations

    catfish, Power, Von, 6, 5

    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
    åĽ½äº§
    -0.10
    éĢ¼
    -0.10
    Ø´ÙĨ
    -0.09
    istream
    -0.09
    ãģĵãģĿ
    -0.08
    åIJİæľŁ
    -0.08
    .synthetic
    -0.08
    éĦ
    -0.08
    æĸ°äº¬æĬ¥
    -0.08
    è¿Ļ对
    -0.08
    POSITIVE LOGITS
    åį°è±¡
    0.09
    té
    0.09
     Nam
    0.09
    æľªæĪIJ
    0.08
     Extras
    0.08
    nam
    0.08
    æ°Ķæģ¯
    0.08
    ities
    0.08
    çī¹æ®Ĭ
    0.08
    ä¸īæĿ¡
    0.08
    Activations Density 0.033%

    No Known Activations