© 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. 6576
    Prev
    Next
    INDEX
    Explanations

    new to programming

    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
    asley
    -0.09
    axed
    -0.09
    èĥ½ä½¿
    -0.09
    å·²æľī
    -0.08
    åı¯æĥľ
    -0.08
    ä¸į让
    -0.08
     indis
    -0.08
    稽
    -0.08
    MBED
    -0.08
    ::__
    -0.08
    POSITIVE LOGITS
    åıªçŁ¥éģĵ
    0.10
    妾
    0.10
    被çĽĹ
    0.10
     Serge
    0.10
    è§īå¾Ĺå¾Ī
    0.09
    æĹłçŁ¥
    0.09
    port
    0.09
    ä¸įæ¸ħæ¥ļ
    0.09
    ä¸įäºĨ解
    0.09
    éĩijèī²
    0.09
    Activations Density 0.120%

    No Known Activations