© 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. 11693
    Prev
    Next
    INDEX
    Explanations

    exploration of, introduction to, collection of

    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
    第ä¸ī次
    -0.10
    éĢĤåIJĪèĩªå·±
    -0.10
    äºĨèĩªå·±çļĦ
    -0.09
    Unchecked
    -0.08
    èķī
    -0.08
    åı¬
    -0.08
    èĩªå·±çļĦ
    -0.08
    ä¼¼ä¹İæĺ¯
    -0.08
    ä¸ĭæīĭ
    -0.08
    afone
    -0.08
    POSITIVE LOGITS
    ä»İæł¹æľ¬ä¸Ĭ
    0.10
    ä¹ĭ举
    0.10
    ä½ĵçİ°
    0.09
    ä»İæł¹æľ¬
    0.09
    atem
    0.09
    çĸĥ
    0.09
    åĩłä¹İæīĢæľī
    0.09
    踩
    0.09
    æµļ
    0.09
    èĢĮéĿŀ
    0.09
    Activations Density 0.104%

    No Known Activations