© 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. 18935
    Prev
    Next
    INDEX
    Explanations

    choice between

    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
    骰
    -0.10
    åľ¨æĹ¥æľ¬
    -0.09
     Eval
    -0.09
    _between
    -0.09
    海岸
    -0.09
    çļĦæ¯ĶèµĽ
    -0.09
    ä¹ĭç¾İ
    -0.09
    éĤĭ
    -0.09
    osos
    -0.09
    çļĦæĪ¿åŃIJ
    -0.09
    POSITIVE LOGITS
    以ä¸ĭåĩłä¸ª
    0.10
    /am
    0.10
    bek
    0.09
    è¿ĩ硬
    0.09
    ä¸Ĭè¿°
    0.08
    aroo
    0.08
    åIJĦ个
    0.08
    ä¸įåIJĮ
    0.08
    çľĭå¾Ĺ
    0.08
    sWith
    0.08
    Activations Density 0.051%

    No Known Activations