© 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. 19288
    Prev
    Next
    INDEX
    Explanations

    three point shooting

    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
    åı¨
    -0.09
    åĴĮå®ĮåĸĦ
    -0.08
    antic
    -0.08
    pw
    -0.08
    /Runtime
    -0.08
    sam
    -0.08
    çĪ¿
    -0.08
    acher
    -0.08
    pressor
    -0.08
    otype
    -0.08
    POSITIVE LOGITS
    éľĸ
    0.09
    è¡·
    0.09
     Mein
    0.08
    ìľ¨
    0.08
     Karn
    0.08
    rees
    0.08
    mani
    0.08
    [in
    0.08
    çļĦæķ´ä½ĵ
    0.08
    zar
    0.08
    Activations Density 0.001%

    No Known Activations