© 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. 38744
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    esc
    -0.08
    深深çļĦ
    -0.08
    éĶ¦æłĩ
    -0.08
    bac
    -0.08
    iosa
    -0.08
    å·´å·´
    -0.08
    ][_
    -0.08
    ieber
    -0.08
    åŃĹåı·
    -0.08
    ActionBar
    -0.08
    POSITIVE LOGITS
    æ«ĥ
    0.09
    æĹ¥åŃIJ
    0.08
    çĤ¹å¤ļ
    0.08
    è¿ĻçĤ¹
    0.08
     ÑģоÑģед
    0.08
    ä¸įæŃ»
    0.08
    å¨ĵ
    0.08
    اÙĨت
    0.08
     Democr
    0.08
    å²Ľ
    0.08
    Activations Density 0.138%

    No Known Activations