© 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. 17923
    Prev
    Next
    INDEX
    Explanations

    league leaders and scoring

    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
    åľį
    -0.10
    ç»Ĩèĩ´
    -0.10
    åĽ´
    -0.09
    åĪº
    -0.09
    íİĢ
    -0.09
    åħŃåIJĪ
    -0.09
    髯
    -0.08
    richt
    -0.08
    åĩłå¤©
    -0.08
    æģ¤
    -0.08
    POSITIVE LOGITS
    寤
    0.09
    -Pack
    0.09
    é«ĺäºİ
    0.09
    åīIJ
    0.09
    .avg
    0.09
    åĩºåħ¥
    0.08
    ä¸Ģæĺ¯
    0.08
    بث
    0.08
    åīľ
    0.08
    èī¯
    0.08
    Activations Density 0.010%

    No Known Activations