© 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. 35140
    Prev
    Next
    INDEX
    Explanations

    opus number and composer references

    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
    pell
    -0.08
    ä¸ŃéĢĶ
    -0.08
     اخت
    -0.08
    heid
    -0.08
     Oak
    -0.08
    æŁ¥çľĭ详æĥħ
    -0.08
     Kan
    -0.08
    GRAM
    -0.08
    cko
    -0.08
    .operations
    -0.08
    POSITIVE LOGITS
    ä¹ĭä½ľ
    0.12
    ä½ľåĵģ
    0.11
    çļĦä½ľåĵģ
    0.10
    鼶ç¢İ
    0.10
    æĩĪ
    0.09
    stück
    0.09
    æĻ¦
    0.09
    æŃª
    0.09
    ä¸Ģé¦ĸ
    0.09
     misc
    0.09
    Activations Density 0.091%

    No Known Activations