© 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. 23477
    Prev
    Next
    INDEX
    Explanations

    start or end

    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
    äºĨåIJĹ
    -0.09
    ä¸Ģçľĭ
    -0.09
    äºĨä¸Ģç³»åĪĹ
    -0.09
    åķĨåĬ¡
    -0.08
    æ¯ĶåĪĨ
    -0.08
     conversations
    -0.08
    åı¯èĥ½æĢ§
    -0.08
    ç³Ł
    -0.08
    äºĨä¸Ģåľº
    -0.08
    æīĭä¸ŃçļĦ
    -0.08
    POSITIVE LOGITS
    ç»ĵæĿŁ
    0.17
    å®Įç»ĵ
    0.14
    å¼Ģå§ĭ
    0.14
    çµIJæĿŁ
    0.14
    ç»ĵæĿŁäºĨ
    0.13
    éĸĭå§ĭ
    0.11
     start
    0.11
    ç»ĵæĿŁåIJİ
    0.11
    ç»ĵ论
    0.11
    à¸Īà¸ļ
    0.11
    Activations Density 0.153%

    No Known Activations