© 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. 33981
    Prev
    Next
    INDEX
    Explanations

    ranking positions

    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
    å²ĺ
    -0.09
    ÑĦеÑĢ
    -0.09
    å®Įåħ¨æĺ¯
    -0.09
    ä¸įæĪIJ
    -0.08
    åĨ³èĥľ
    -0.08
    å¤ĸåĩº
    -0.08
    สาร
    -0.08
    åĹ£
    -0.08
    iter
    -0.08
     vic
    -0.08
    POSITIVE LOGITS
    æİĴåIJį
    0.18
    rank
    0.18
    æİĴåIJį第
    0.16
    ä½įåĪĹ
    0.16
     rank
    0.16
    ä½įç½®
    0.16
     ranking
    0.15
     rankings
    0.15
     Rankings
    0.14
     ranks
    0.14
    Activations Density 0.097%

    No Known Activations