© 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. 38067
    Prev
    Next
    INDEX
    Explanations

    United States citations

    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
    è·¨çķĮ
    -0.09
    纡
    -0.09
    orses
    -0.08
    çŁį
    -0.08
    earn
    -0.08
    å®Ŀå®ī
    -0.08
    妪
    -0.07
     اÙĦÙħسÙĦÙħ
    -0.07
    avn
    -0.07
    æĭľ
    -0.07
    POSITIVE LOGITS
    èĵĵ
    0.10
    æı©
    0.09
    溲
    0.09
    èªķ
    0.09
     accom
    0.09
    çļĦéĤ£ç§į
    0.09
    éľĵ
    0.09
    å§Ķ书记
    0.09
    æĵĶ
    0.09
    ÑĪиÑĢ
    0.08
    Activations Density 0.161%

    No Known Activations