© 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. 36105
    Prev
    Next
    INDEX
    Explanations

    accurate, accredited, accordion

    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
    ../
    -0.11
    attles
    -0.10
    wart
    -0.10
    ../../../
    -0.10
    çŃ·
    -0.10
    ãģĵãģ¨
    -0.10
    orris
    -0.10
    ì¼ĵ
    -0.09
    од
    -0.09
    arity
    -0.09
    POSITIVE LOGITS
    uate
    0.10
    .Acc
    0.10
    ãģªãģĬ
    0.10
    äºĭæĥħ
    0.09
    idental
    0.09
    ords
    0.09
    ound
    0.09
    омеÑĢ
    0.09
    uated
    0.09
    丰
    0.08
    Activations Density 0.033%

    No Known Activations