© 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. 58856
    Prev
    Next
    INDEX
    Explanations

    accessing resources and data

    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
    tog
    -0.09
    é¢ĦæľŁ
    -0.08
    åĬŁå¤«
    -0.08
    举åĬ¨
    -0.08
    å®ļåIJij
    -0.08
    еÑģп
    -0.08
    è²Į
    -0.08
     paging
    -0.08
    NS
    -0.08
    _Bl
    -0.08
    POSITIVE LOGITS
    æķĻèĤ²èµĦæºIJ
    0.13
     resources
    0.11
    (access
    0.11
    æĽ´å¤ļ精彩
    0.10
    via
    0.10
    å°ı康社ä¼ļ
    0.09
    èµĦæºIJ
    0.09
    ç¦ģåĮº
    0.09
    åĽ½éĻħå¸Ĥåľº
    0.09
    еÑĤÑĮ
    0.09
    Activations Density 0.112%

    No Known Activations