© 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. 30503
    Prev
    Next
    INDEX
    Explanations

    source code or binary forms

    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
    æĹłèģĬ
    -0.10
    æĬĢå¸Ī
    -0.09
    æ¯Ģ
    -0.09
    继
    -0.08
     arp
    -0.08
    æĹ¥å¤ľ
    -0.08
    ements
    -0.08
    æ¯ģ
    -0.08
     Fate
    -0.08
    ÙħÙĤ
    -0.08
    POSITIVE LOGITS
    迸
    0.09
    å®ļä½į
    0.09
    .PARAM
    0.08
    _lifetime
    0.08
    ç«ĻçĿĢ
    0.08
     Basis
    0.08
    é¾ĻéŨ
    0.08
    ç§įç§į
    0.08
     basis
    0.08
    ä¸įåħį
    0.08
    Activations Density 0.016%

    No Known Activations