© 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. 32326
    Prev
    Next
    INDEX
    Explanations

    code output comments

    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
    åĪ°ä½į
    -0.11
    ä¸Ńæľī
    -0.10
    i
    -0.10
    ÑĤÑı
    -0.09
     ESC
    -0.09
    äºĨ解åĪ°
    -0.09
    lew
    -0.08
    æĮ¡
    -0.08
    åŃĶéĽĢ
    -0.08
     pud
    -0.08
    POSITIVE LOGITS
    ivar
    0.11
    pire
    0.10
    åı¯åľ¨
    0.10
    æľĢç»Ī
    0.09
    awn
    0.09
    ç»ĵå±Ģ
    0.08
    åIJİèĢħ
    0.08
    夺
    0.08
    å¤ľéĩĮ
    0.08
    æľĢçµĤ
    0.08
    Activations Density 0.122%

    No Known Activations