© 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. 58348
    Prev
    Next
    INDEX
    Explanations

    Ruby PATH Aptana

    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
    å¼Ģæľº
    -0.09
    vide
    -0.09
    é«ĺæĺĤ
    -0.09
    çŀ§
    -0.09
    æķ´ä¸ªäºº
    -0.09
     ×ĵ×ķ
    -0.09
    åĭī强
    -0.09
    åºĨ幸
    -0.09
    å¼Ģè¾Ł
    -0.09
    æĮĤçĿĢ
    -0.08
    POSITIVE LOGITS
    _travel
    0.08
    åĶIJ
    0.08
    èĤ©è´Ł
    0.08
    æıŃ
    0.08
    TRL
    0.08
    èĸĦ
    0.08
    æ¸ħæī«
    0.08
    Crit
    0.08
    _take
    0.08
     rivals
    0.08
    Activations Density 0.054%

    No Known Activations