© 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. 55518
    Prev
    Next
    INDEX
    Explanations

    not officially / provided by

    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
    ç¼Ń
    -0.09
    _RING
    -0.09
    éĢĸ
    -0.09
    èĩ´åij½
    -0.09
    åı¯è§Ĥ
    -0.08
    สาย
    -0.08
    森
    -0.08
    elan
    -0.08
    erten
    -0.08
    .mainloop
    -0.08
    POSITIVE LOGITS
    ä»ħ为
    0.13
    ä»ħä¾ĽåıĤèĢĥ
    0.12
     merely
    0.11
    ä¹Łä¸įæĺ¯
    0.11
    æĺ¯ä¸ºäºĨ
    0.11
    åıªæĺ¯ä¸ºäºĨ
    0.11
    ä¸įè¿ĩæĺ¯
    0.11
    æĪijåıªæĺ¯
    0.10
    ä»ħ
    0.10
    ä¹Łä¸į
    0.10
    Activations Density 0.099%

    No Known Activations