© 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. 18108
    Prev
    Next
    INDEX
    Explanations

    With the

    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
    èĻİ
    -0.10
    ä½Ĺ
    -0.09
    éĢ®
    -0.09
     ожида
    -0.09
    .ptr
    -0.08
    æĽ´å®¹æĺĵ
    -0.08
    ÑĢÑĥÑĤ
    -0.08
    çĪ¸
    -0.08
    xCA
    -0.08
    ARAM
    -0.08
    POSITIVE LOGITS
    fac
    0.09
    ä¸įåģļ
    0.09
    izen
    0.09
    _userid
    0.08
    æģŃåĸľ
    0.08
    åľ¨äº¬
    0.08
    å¢Ļå£ģ
    0.08
     date
    0.08
    ecz
    0.08
    æĹ¥æľŁ
    0.08
    Activations Density 0.009%

    No Known Activations