© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21336
    Prev
    Next
    INDEX
    Explanations

    above

    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
    究竣æĺ¯
    -0.10
    çļĦç¡®æĺ¯
    -0.09
    kim
    -0.09
    å°ıåŀĭ
    -0.09
    makers
    -0.08
    æ¯Ķå¦Ĥ说
    -0.08
    UCE
    -0.08
    ÑĢÑĥÑĩ
    -0.08
    大åŀĭ
    -0.07
    ç¡®
    -0.07
    POSITIVE LOGITS
    ä¸Ĭè¿°
    0.25
    åīįè¿°
    0.24
     above
    0.22
     вÑĭÑĪе
    0.19
    以ä¸Ĭ
    0.19
    above
    0.18
    ä¸ĬéĿ¢
    0.18
    Above
    0.17
    以ä¸ĬçļĦ
    0.17
     Above
    0.17
    Activations Density 0.130%

    No Known Activations