© 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. 21653
    Prev
    Next
    INDEX
    Explanations

    Dixon, Dickson, zxing, ZX Spectrum

    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
    ìĦł
    -0.10
    Ø´ÙĬ
    -0.10
    bert
    -0.09
    _PAD
    -0.09
    ena
    -0.09
    ä¸ĢåIJ¬
    -0.09
    PAD
    -0.08
    çĹ´
    -0.08
    pid
    -0.08
    ved
    -0.08
    POSITIVE LOGITS
    anders
    0.11
    幺
    0.10
    toa
    0.09
     WithEvents
    0.09
     Uncategorized
    0.09
    lâ
    0.09
    lö
    0.08
    ãģįãģ£ãģ¨
    0.08
    onor
    0.08
    mund
    0.08
    Activations Density 0.001%

    No Known Activations