© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6913
    Prev
    Next
    INDEX
    Explanations

    code punctuation and common programming terms

    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
    ä¸įå®ļ
    -0.11
     моменÑĤ
    -0.09
    å²IJ
    -0.09
    2
    -0.09
    tro
    -0.08
    å¦Ĥä½ķçľĭå¾ħ
    -0.08
    4
    -0.08
    3
    -0.08
     STDERR
    -0.08
    å®ļäºĨ
    -0.08
    POSITIVE LOGITS
    好åIJĹ
    0.10
    å¿«è¦ģ
    0.09
    _almost
    0.09
    åħ¶æīĢ
    0.09
    èĩªå·±çļĦ
    0.09
    对她
    0.08
    gether
    0.08
    çİ°æľīçļĦ
    0.08
    æĥħåĨµè¿Ľè¡Į
    0.08
    å¹³æŶ
    0.08
    Activations Density 0.918%

    No Known Activations