© 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. 10752
    Prev
    Next
    INDEX
    Explanations

    whether

    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
    è¡¥é½IJ
    -0.09
    è¡ħ
    -0.09
    eded
    -0.09
    æĪĸ许
    -0.09
    çĶļèĩ³è¿ŀ
    -0.08
    ä¹ŁåĽłæѤ
    -0.08
    æĿĤ
    -0.08
    awi
    -0.08
    åĽłèĢĮ
    -0.08
    èĢĮè¿Ļ
    -0.08
    POSITIVE LOGITS
    æľīæĽ´å¥½çļĦ
    0.12
    ä»ħä»ħæĺ¯
    0.11
    åIJ¦
    0.10
    ä»ħä»ħ
    0.10
     something
    0.10
    something
    0.09
    åħ¶å®ĥ
    0.09
    /from
    0.09
    åħ¶ä½Ļ
    0.09
    人éĹ´
    0.09
    Activations Density 0.072%

    No Known Activations