© 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. 6957
    Prev
    Next
    INDEX
    Explanations

    published on

    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
    æĢķ
    -0.10
    åıªæĢķ
    -0.09
    èĦ¯
    -0.08
    åıªèĥ½è¯´
    -0.08
    outh
    -0.08
    ç¨įç¨į
    -0.08
    å·¥ä½ľèĢħ
    -0.08
    æ³¼
    -0.08
    UPI
    -0.08
    lected
    -0.07
    POSITIVE LOGITS
    ellas
    0.10
    æĢĢæĬ±
    0.10
    uien
    0.09
    icle
    0.09
    imately
    0.09
    _HS
    0.09
    è°İ
    0.09
    uis
    0.09
    éĹ½
    0.09
    _INCLUDE
    0.08
    Activations Density 0.002%

    No Known Activations