© 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. 30492
    Prev
    Next
    INDEX
    Explanations

    ready for use or action

    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
    漪
    -0.09
    ä¼ĺç§ĢçļĦ
    -0.09
    è§īå¾Ĺèĩªå·±
    -0.09
    çĬĢ
    -0.09
    æĪIJè´¥
    -0.09
    欻
    -0.09
    oyer
    -0.09
     Nay
    -0.09
    éĢŁåº¦å¿«
    -0.09
    ulator
    -0.09
    POSITIVE LOGITS
    ä¸ĭä¸ĢæŃ¥
    0.10
    åijĪçİ°
    0.10
    åijĪçı¾
    0.09
    ä¸ĭ次
    0.09
     Canter
    0.09
    Criterion
    0.08
    åľ¨æľªæĿ¥
    0.08
     ëĭ¤ìĿĮ
    0.08
    è¾ĵéĢģ
    0.08
    etta
    0.08
    Activations Density 0.020%

    No Known Activations