© 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. 31233
    Prev
    Next
    INDEX
    Explanations

    non refundable, renewable, refund

    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
    å¾Ħ
    -0.10
    éľģ
    -0.10
    é¦ĸåıij
    -0.09
    ç½¢
    -0.08
    æĢİä¹Īæł·
    -0.08
    åıĬ缸åħ³
    -0.08
    æĿł
    -0.08
     fortune
    -0.08
    尽快
    -0.08
    头ä¸Ĭ
    -0.08
    POSITIVE LOGITS
    apos
    0.11
    åıĭ们
    0.10
    parison
    0.09
    ç²¾èĭ±
    0.09
    约ä¼ļ
    0.09
    agh
    0.09
    ozo
    0.08
    hausen
    0.08
    ront
    0.08
    åĢĴå¡Į
    0.08
    Activations Density 0.006%

    No Known Activations