© 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. 58767
    Prev
    Next
    INDEX
    Explanations

    no or zero

    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
    rays
    -0.09
    åĪĢ
    -0.09
     Ren
    -0.08
    湿润
    -0.08
    å¤ļç§į
    -0.08
    ls
    -0.08
    éĴ®
    -0.08
    æĢ»éĿ¢ç§¯
    -0.08
    æľ´ç´ł
    -0.08
    semblies
    -0.08
    POSITIVE LOGITS
     поб
    0.10
    /no
    0.10
    .zero
    0.10
    _none
    0.09
     aucun
    0.09
    ZERO
    0.09
    å¬ĸ
    0.09
    NIL
    0.09
     zero
    0.09
    å¥Ń
    0.09
    Activations Density 0.212%

    No Known Activations