© 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. 53051
    Prev
    Next
    INDEX
    Explanations

    something special or capable

    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
     vic
    -0.08
    _pending
    -0.08
    edBy
    -0.08
    aji
    -0.08
    ç®ķ
    -0.08
    éļĶå£ģ
    -0.08
     argent
    -0.07
    éĢĹ
    -0.07
     adj
    -0.07
    ä¸Ģéĺµ
    -0.07
    POSITIVE LOGITS
    æĹ¢æĺ¯
    0.12
    æĹ¢èĥ½
    0.11
    ä¸įä»ħæĺ¯
    0.10
    äºĨä¸Ģ个
    0.10
    å¼Ģå±ķäºĨ
    0.10
    äºĨä¸Ģåľº
    0.10
    饮åĵģ
    0.10
    æ©Ľ
    0.10
    çĭ¬ä¸ĢæĹłäºĮ
    0.09
    çļĦä½ľåĵģ
    0.09
    Activations Density 0.354%

    No Known Activations