© 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. 23549
    Prev
    Next
    INDEX
    Explanations

    approval or approve user

    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
    ongyang
    -0.10
    离
    -0.09
    æĦĨ
    -0.09
     differentiated
    -0.09
    åī¯å¸Ĥéķ¿
    -0.09
    ç¯Ĩ
    -0.09
    ç¨į
    -0.09
    eness
    -0.09
    ikit
    -0.09
    æ»´
    -0.09
    POSITIVE LOGITS
     Markus
    0.10
    rees
    0.09
    éĢīçĶ¨
    0.08
    à¸Ĺา
    0.08
    _flutter
    0.08
    Minor
    0.08
     REPL
    0.08
     Yad
    0.08
    æݾ
    0.08
    年轻人
    0.08
    Activations Density 0.001%

    No Known Activations