© 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. 35330
    Prev
    Next
    INDEX
    Explanations

    creator/owner/author

    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
    дÑĢа
    -0.09
    кÑģ
    -0.09
    orris
    -0.09
    encia
    -0.08
    æĮ½
    -0.08
    è¾ĩ
    -0.08
    èĽĨ
    -0.08
    樽
    -0.08
    whel
    -0.08
    åı£åı·
    -0.08
    POSITIVE LOGITS
    å½ĵäºĭ人
    0.17
    å½ĵäºĭ
    0.16
    ä½ľèĢħæľ¬äºº
    0.15
    åİĤ家
    0.12
    æľ¬äºº
    0.12
     owners
    0.11
    éĤ£ä¸ªäºº
    0.11
    åįĸ家
    0.11
    çĶŁäº§åİĤ家
    0.11
    ä½ľèĢħ
    0.11
    Activations Density 0.122%

    No Known Activations