© 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. 58766
    Prev
    Next
    INDEX
    Explanations

    parenthesized clarifications

    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
    æ¯ķç«Ł
    -0.10
    æĶ¸
    -0.10
    кÑĥ
    -0.10
     ведÑĮ
    -0.09
    è¿Ī
    -0.08
    .Apis
    -0.08
    æ°´èĤ¿
    -0.08
    odus
    -0.08
    udit
    -0.08
    uds
    -0.08
    POSITIVE LOGITS
    leet
    0.09
     discipline
    0.08
     Sob
    0.08
    orney
    0.08
     pr
    0.07
    èĢĮåĩº
    0.07
    大åıij
    0.07
    主ä¹īæĢĿæĥ³
    0.07
    çĽ¸å¯¹è¾ĥ
    0.07
    é«ĺæ½®
    0.07
    Activations Density 0.123%

    No Known Activations