© 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. 61310
    Prev
    Next
    INDEX
    Explanations

    much followed by descriptive words

    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
    oid
    -0.09
    ä¸įè´Ł
    -0.09
    æĪ¿
    -0.08
    è°ģ
    -0.08
    æ´¾
    -0.08
    atest
    -0.08
    èĪĴ
    -0.08
    毫æĹłçĸijéĹ®
    -0.08
    主è¦ģæľī
    -0.08
    -than
    -0.08
    POSITIVE LOGITS
    åīįæıIJæĺ¯
    0.10
    æĺ¯ä¸ºäºĨ
    0.10
    åıĸåĨ³äºİ
    0.10
    _printf
    0.10
    åľ¨äºİ
    0.10
    ä¸İæŶ
    0.10
     effort
    0.10
    ãģıãģªãĤĬ
    0.09
    ãĥ¥
    0.09
    å·²åľ¨
    0.09
    Activations Density 0.023%

    No Known Activations