© 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. 19082
    Prev
    Next
    INDEX
    Explanations

    approval or endorsement

    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
    æĬ½
    -0.10
    otics
    -0.09
    ç¼´
    -0.09
    inati
    -0.09
    assis
    -0.08
    ä¸¥æł¼èIJ½å®ŀ
    -0.08
    èĴĤ
    -0.08
    å¾Īæĥ³
    -0.08
    ographies
    -0.08
    ags
    -0.08
    POSITIVE LOGITS
    æī¹åĩĨ
    0.20
    认åı¯
    0.19
     approval
    0.17
     Approval
    0.15
     approve
    0.14
    çļĦ认åı¯
    0.14
    认åIJĮ
    0.14
    èµŀåIJĮ
    0.14
     approved
    0.14
     approves
    0.13
    Activations Density 0.070%

    No Known Activations