© 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. 58851
    Prev
    Next
    INDEX
    Explanations

    long jump or pole vault clearance

    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
     shocks
    -0.09
    æıŃéľ²
    -0.09
    æ®ĭ
    -0.09
    èµĭ
    -0.08
    ä¸įåĩºæĿ¥
    -0.08
    AAA
    -0.08
     Afro
    -0.08
    åĶĨ
    -0.08
    åĩºæĿ¥
    -0.07
    åī©ä½Ļ
    -0.07
    POSITIVE LOGITS
    è·³
    0.12
    éĻ¢åŃIJ
    0.10
    _hop
    0.10
    ä¸ĢåŃĹ
    0.10
    _DISPATCH
    0.09
    ensch
    0.09
    å¿ĥçIJĨåģ¥åº·
    0.09
    åIJIJ
    0.09
    _SCOPE
    0.09
    çŁ¥åIJįåĵģçīĮ
    0.09
    Activations Density 0.041%

    No Known Activations