© 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. 58485
    Prev
    Next
    INDEX
    Explanations

    critics say

    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
    OperationException
    -0.09
    ensem
    -0.09
    Ãłng
    -0.08
    .mods
    -0.08
    åºĨ
    -0.08
    èģĶç½ij
    -0.08
    ä»£è¡¨åĽ¢
    -0.08
    涿
    -0.08
    OMIC
    -0.08
    itur
    -0.08
    POSITIVE LOGITS
    说æĪij
    0.13
     Hell
    0.09
    æĤłæĤł
    0.09
    WithValue
    0.09
    ä¼ļ使
    0.09
    讥
    0.09
     proport
    0.08
    atat
    0.08
    说èĩªå·±
    0.08
    说æĺ¯
    0.08
    Activations Density 0.017%

    No Known Activations