© 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. 57361
    Prev
    Next
    INDEX
    Explanations

    as well as

    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
    太快
    -0.11
     благ
    -0.10
    dez
    -0.10
    енн
    -0.10
    è¿ĺä¸įå¦Ĥ
    -0.10
    éĺ¶çº§
    -0.10
    loquent
    -0.10
    éĤ£æŶåĢĻ
    -0.10
     equiv
    -0.09
    argin
    -0.09
    POSITIVE LOGITS
     unsur
    0.08
    око
    0.08
    åı¯æĥ³èĢĮçŁ¥
    0.08
    åĺĽ
    0.08
    aat
    0.08
    è¿ĺæľī
    0.08
    ä¹Łå¾Ī
    0.08
    utom
    0.08
    大æ¦Ĥ
    0.07
     stated
    0.07
    Activations Density 0.063%

    No Known Activations