© 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. 2438
    Prev
    Next
    INDEX
    Explanations

    number formatting

    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
    ðŁı»
    -0.12
    owers
    -0.11
    undry
    -0.10
    é«ĺæłĩåĩĨ
    -0.09
    è·Ŀ
    -0.09
    allon
    -0.09
    èĭ¥æľī
    -0.09
    eward
    -0.09
    姥
    -0.09
    snow
    -0.09
    POSITIVE LOGITS
    thon
    0.11
     crunch
    0.11
    ical
    0.11
    ofday
    0.10
    inous
    0.09
    BERS
    0.09
    FormatException
    0.09
     Crunch
    0.09
    less
    0.09
    ismatic
    0.09
    Activations Density 0.191%

    No Known Activations