© 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. 48294
    Prev
    Next
    INDEX
    Explanations

    movements and traditions

    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
    æ¯ıéĢ¢
    -0.08
    9
    -0.08
    åĮĸ
    -0.08
    è±Ĩ
    -0.08
    8
    -0.08
    3
    -0.08
    .neg
    -0.08
    7
    -0.07
     Composer
    -0.07
    æ¸ħæ¥ļ
    -0.07
    POSITIVE LOGITS
    æ´¾
    0.15
    åĪĨæĶ¯
    0.14
    纪
    0.11
    çĻ¾å®¶
    0.11
    ä¸ĢéŨ
    0.11
    æ²IJ
    0.10
    殳
    0.10
    stile
    0.10
     branch
    0.10
    éĺµèIJ¥
    0.10
    Activations Density 0.089%

    No Known Activations