© 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. 52490
    Prev
    Next
    INDEX
    Explanations

    audio files and software

    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
    ellig
    -0.09
    å´Ĥ
    -0.09
    ä¸ĢæĿ¯
    -0.09
    æ»ĭ
    -0.08
    æµĵæµĵçļĦ
    -0.08
    åħħæĸ¥
    -0.08
    è¾ĺ
    -0.08
     иÑģкÑĥÑģ
    -0.08
    opic
    -0.08
    -style
    -0.08
    POSITIVE LOGITS
    æīĵåĩ»
    0.11
    é¼ĵ
    0.10
    躬
    0.10
    éĢĨ
    0.10
    peq
    0.09
    _props
    0.09
     Svg
    0.09
    éĿ¢è¯ķ
    0.09
    lyph
    0.09
    /native
    0.09
    Activations Density 0.080%

    No Known Activations