© 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. 50348
    Prev
    Next
    INDEX
    Explanations

    py and subsequent syllables

    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
     trú
    -0.09
    nbsp
    -0.09
    éĻ¢æł¡
    -0.09
    sworth
    -0.08
    olk
    -0.08
    amp
    -0.08
    okie
    -0.08
     vag
    -0.08
    aid
    -0.08
    inner
    -0.08
    POSITIVE LOGITS
    ramid
    0.16
    ramids
    0.12
    thag
    0.11
    èĩªåľ¨
    0.10
    itive
    0.10
    ridor
    0.09
    pone
    0.09
    0.09
    åķī
    0.09
    folio
    0.09
    Activations Density 0.083%

    No Known Activations