© 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. 21718
    Prev
    Next
    INDEX
    Explanations

    Col + suffixes

    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
    ment
    -0.10
    melon
    -0.10
    ÙħÙĪÙĦ
    -0.09
    nger
    -0.09
    ãģıãĤĮ
    -0.09
    edly
    -0.09
    ORS
    -0.09
    uality
    -0.09
    imonial
    -0.09
     воÑĤ
    -0.09
    POSITIVE LOGITS
    iseum
    0.13
    ombo
    0.13
    ossal
    0.13
    ibri
    0.11
    åŃIJéĩĮ
    0.11
    LECTION
    0.10
    nect
    0.10
    为空
    0.09
     gắng
    0.09
    lected
    0.09
    Activations Density 0.066%

    No Known Activations