© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7458
    Prev
    Next
    INDEX
    Explanations

    links and involvement

    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
     Ella
    -0.09
     pog
    -0.09
    .fm
    -0.09
    ä¸Ĭç½ij
    -0.08
    Ñģка
    -0.08
    ÑģоÑģ
    -0.08
    .dm
    -0.08
     dissect
    -0.08
    ell
    -0.08
    æĭ¥
    -0.08
    POSITIVE LOGITS
    éĴ£
    0.09
    ç³Ĭæ¶Ĥ
    0.09
    åIJĮä¸Ģ
    0.09
    ammad
    0.09
    ä¸īæĿ¡
    0.08
    éĶī
    0.08
    å¢ĥå¤ĸ
    0.08
    ä¸Ģ头
    0.08
    odian
    0.08
    YN
    0.08
    Activations Density 0.044%

    No Known Activations