© 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. 33307
    Prev
    Next
    INDEX
    Explanations

    Karma yoga

    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
     Boo
    -0.08
    ä¸ī级
    -0.08
    olle
    -0.08
    ä¸Ļ
    -0.08
    æīģ
    -0.08
     Flake
    -0.08
     Exact
    -0.08
    ä½łè§īå¾Ĺ
    -0.08
    SKI
    -0.07
    åĬ²
    -0.07
    POSITIVE LOGITS
    åľĨ满å®ĮæĪIJ
    0.09
    çİ°åĩº
    0.09
    èµĬ
    0.09
    æļĦ
    0.08
    _heading
    0.08
    aller
    0.08
    cheme
    0.08
    æijĺ
    0.08
    奸
    0.08
    æĭĽèģĺä¿¡æģ¯
    0.08
    Activations Density 0.167%

    No Known Activations