© 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. 55940
    Prev
    Next
    INDEX
    Explanations

    RedSquaree

    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
     bó
    -0.10
    ç¡®
    -0.10
    urus
    -0.10
    ä¸įå¿ħè¦ģçļĦ
    -0.09
    çİ©ç¬ij
    -0.09
    ãĥ¼ãĥ³
    -0.09
    ç¬ij容
    -0.09
    TimeInterval
    -0.09
     Gould
    -0.09
    çĪ±æĥħ
    -0.09
    POSITIVE LOGITS
    _LS
    0.09
    çĶ©
    0.09
    çļĦçĥŃæĥħ
    0.09
    é¢Ĩ
    0.09
    æŃ¤äºº
    0.09
    åĮ¿åIJį
    0.08
    éĤ£ä¸ªäºº
    0.08
    羣è¯ļ
    0.08
    ç½ijåıĭ
    0.08
     who
    0.08
    Activations Density 0.083%

    No Known Activations