© 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. 21349
    Prev
    Next
    INDEX
    Explanations

    do our best

    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
    éĢį
    -0.10
    LEC
    -0.09
    åŁ¹
    -0.09
    æµģæ°´
    -0.09
    纪å¾ĭ
    -0.08
    _helpers
    -0.08
    åŀĤ
    -0.08
    æłijç«ĭ
    -0.08
    å²IJ
    -0.08
    æѧ
    -0.08
    POSITIVE LOGITS
    å°½åĬĽ
    0.20
    å°½åı¯èĥ½
    0.16
    å°½
    0.15
    å°½éĩı
    0.14
    æľĢ大ç¨ĭ度
    0.13
    çĽ¡
    0.12
    æľĢ大éĻIJ度
    0.12
    åĦĺ
    0.11
    BEST
    0.11
    åħ¨åĬĽ
    0.11
    Activations Density 0.056%

    No Known Activations