© 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. 55394
    Prev
    Next
    INDEX
    Explanations

    at http

    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
    lobal
    -0.10
     noqa
    -0.10
    éĿ¢çĽ®
    -0.09
    çŃĴ
    -0.09
    à¹Ģม
    -0.08
    æľĢåĸľæ¬¢
    -0.08
    æľĢ容æĺĵ
    -0.08
    íħĮ
    -0.08
     deb
    -0.08
    elter
    -0.08
    POSITIVE LOGITS
    èĥ½æī¾åĪ°
    0.10
    çĵł
    0.09
    :http
    0.09
    æĬķæĶ¾
    0.09
    izzling
    0.09
    鸳
    0.09
    åħ±åĴĮåĽ½
    0.09
    ledged
    0.08
     http
    0.08
    oyer
    0.08
    Activations Density 0.037%

    No Known Activations