© 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. 54478
    Prev
    Next
    INDEX
    Explanations

    name =

    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
    æ³IJ
    -0.08
    _SDK
    -0.08
    rag
    -0.08
    æ§İ
    -0.08
     Clerk
    -0.08
     Tib
    -0.08
    ç¾Ĭæ¯Ľ
    -0.08
    衲
    -0.08
    _VOLUME
    -0.08
     Bark
    -0.08
    POSITIVE LOGITS
    åħŃåIJĪ
    0.10
    :title
    0.09
    uell
    0.09
    SetTitle
    0.09
    çĥĽ
    0.09
     pageTitle
    0.09
     outr
    0.09
    ä½ľèĢħæľ¬äºº
    0.09
    çIJ¥
    0.08
    æĬĵ
    0.08
    Activations Density 0.370%

    No Known Activations