© 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. 4886
    Prev
    Next
    INDEX
    Explanations

    groups and clubs

    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
    inar
    -0.09
    endo
    -0.09
    ugin
    -0.09
    å°ijåIJĥ
    -0.09
    åĶ¤éĨĴ
    -0.08
     Garrison
    -0.08
    anto
    -0.08
    ervo
    -0.08
    endon
    -0.08
    羣çĪ±
    -0.08
    POSITIVE LOGITS
    æļ
    0.09
    é¢Ĩè¢ĸ
    0.09
    éķ¿å¯¿
    0.09
    åıĭ们
    0.09
    ç»Ħéķ¿
    0.08
    _interaction
    0.08
     пÑĢинима
    0.08
    esion
    0.08
    æĻ¤
    0.08
    éķ¶
    0.08
    Activations Density 0.032%

    No Known Activations