© 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. 39623
    Prev
    Next
    INDEX
    Explanations

    there sits/sat/stand

    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
    缴éĢļ车
    -0.12
    æĪ¾
    -0.10
    æŃ£ä¹ī
    -0.10
    ä¸ĭæ»ij
    -0.09
    æĿ¥ä¸´
    -0.09
    æĿ¥æī¾
    -0.09
    è¿ĻæĶ¯
    -0.09
    ç»ĦæĪIJéĥ¨åĪĨ
    -0.09
    æľ¦èĥ§
    -0.09
    å¤ļå¤ļ
    -0.09
    POSITIVE LOGITS
    ISH
    0.09
    ahl
    0.08
     tic
    0.08
    _dicts
    0.08
    iben
    0.08
    sWith
    0.08
    ibs
    0.08
    _UD
    0.08
    otor
    0.08
    Úº
    0.08
    Activations Density 0.016%

    No Known Activations