© 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. 62419
    Prev
    Next
    INDEX
    Explanations

    æ¸ĺ

    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
     unw
    -0.10
    çŁ¥éģĵèĩªå·±
    -0.09
    å¼Ľ
    -0.09
     Eg
    -0.08
    åįģä¸īå±Ĭ
    -0.08
    .annot
    -0.08
    åĬłæ·±
    -0.08
    æĿĤ
    -0.08
    ENE
    -0.08
    pekt
    -0.08
    POSITIVE LOGITS
    æ¸Ĺ
    0.09
    æłĩæĿĨ
    0.09
    å°º
    0.09
    è¹²
    0.09
    æĹłæķĮ
    0.09
    éĽ¨æ°´
    0.08
    ÑĩаÑĤ
    0.08
    åIJĮä»ģ
    0.08
    çĶŁåij½çļĦ
    0.08
    æ¸ĹéĢı
    0.08
    Activations Density 0.042%

    No Known Activations