© 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. 33721
    Prev
    Next
    INDEX
    Explanations

    how to get

    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
    çĿ£
    -0.10
    æŃ·
    -0.09
    ãģIJ
    -0.09
    icas
    -0.09
    ç¥ł
    -0.09
    ica
    -0.09
    æģŃåĸľ
    -0.08
     trÆ°á»Łng
    -0.08
    å¥ī
    -0.08
    ixer
    -0.08
    POSITIVE LOGITS
    çīĪ
    0.09
    ä¸į让
    0.09
    缸ç»ĵåIJĪ
    0.09
    说æľį
    0.09
    ?action
    0.09
    åijľ
    0.09
    åĺ´å·´
    0.08
    ä¸įä¿¡
    0.08
     rid
    0.08
    ä¸įçĽ¸ä¿¡
    0.08
    Activations Density 0.056%

    No Known Activations