© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51841
    Prev
    Next
    INDEX
    Explanations

    classification, detection, separation, authentication

    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
    -lined
    -0.11
    ä¸į足以
    -0.09
    å±Ī
    -0.09
    /apis
    -0.09
    对该
    -0.09
    å°ıå°ıçļĦ
    -0.09
    马åĬĽ
    -0.09
    丰å¯Įå¤ļ彩
    -0.09
    æĸĭ
    -0.08
    è¿IJè´¹
    -0.08
    POSITIVE LOGITS
    èĥ½åĬĽå¼º
    0.09
    via
    0.09
    without
    0.08
    ä¸Ģ缴éĥ½æĺ¯
    0.08
    åĢŁåĬ©
    0.08
    ä½ĵ系建设
    0.08
    par
    0.08
    è¿ĩç¨ĭå½ĵä¸Ń
    0.08
    çŃīé¢ĨåŁŁ
    0.08
     without
    0.08
    Activations Density 0.580%

    No Known Activations