© 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. 57704
    Prev
    Next
    INDEX
    Explanations

    ice skating and sports

    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
    ven
    -0.09
    åIJį声
    -0.09
    олÑĮ
    -0.09
    åIJijä¸Ĭ
    -0.09
    åı£è¢ĭ
    -0.08
    eger
    -0.08
    -tags
    -0.08
    æĪij们ä¸Ģèµ·
    -0.08
    -price
    -0.08
    åħ±æľī
    -0.08
    POSITIVE LOGITS
    çĨ¨
    0.09
    ç§ĭåĨ¬
    0.09
    åı®
    0.09
    çĹķ
    0.09
    idth
    0.09
    èĢģçĪ·
    0.09
    å¢ĥ
    0.09
    boys
    0.09
     Bethlehem
    0.09
    åĮĸå¦Ĩåĵģ
    0.09
    Activations Density 0.136%

    No Known Activations