© 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. 9795
    Prev
    Next
    INDEX
    Explanations

    .Col access and Position

    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
    æł¸åĩĨ
    -0.09
     اÙĦÙħص
    -0.09
     fran
    -0.09
    Ä°Åŀ
    -0.08
    ulta
    -0.08
    ondo
    -0.08
    åĬĽæ±Ĥ
    -0.08
    å¸Ŀçİĭ
    -0.08
    .yy
    -0.08
     Palace
    -0.08
    POSITIVE LOGITS
    ä¼ij
    0.10
    idget
    0.10
    ìĤ¬ìĿ´
    0.09
    edic
    0.09
    æĬĢæľ¯æĶ¯æĮģ
    0.09
    urv
    0.09
    å¿ĥçģµ
    0.09
    åij½
    0.09
     Bs
    0.08
    yat
    0.08
    Activations Density 0.067%

    No Known Activations