© 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. 33572
    Prev
    Next
    INDEX
    Explanations

    metal objects and fastenings

    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
    èĬĿ
    -0.10
    è¡£
    -0.09
    åĮĸèĤ¥
    -0.09
    ä¸įåģļ
    -0.09
    æĹ¢æľī
    -0.09
    认
    -0.08
    辩论
    -0.08
    ->[
    -0.08
    çªĹå¸ĺ
    -0.08
    æĶ¾å¼Ģ
    -0.08
    POSITIVE LOGITS
    umbo
    0.09
    var
    0.08
    èµ¢å¾Ĺ
    0.08
    .toLocale
    0.08
    pur
    0.08
    é«ĺéĵģ
    0.08
    ä¸ŃæľŁ
    0.08
    اØ
    0.08
    å¯ĨéĽĨ
    0.08
     Zum
    0.08
    Activations Density 0.068%

    No Known Activations