© 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. 49015
    Prev
    Next
    INDEX
    Explanations

    magazine publications and related entities

    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
    å¥Ķ
    -0.09
    ä¹IJ趣
    -0.08
    éĶħ
    -0.08
    /free
    -0.08
     libert
    -0.08
    æĿ¥èĩª
    -0.08
    lest
    -0.08
    å·´æĸ¯
    -0.07
    åıĹ访èĢħ
    -0.07
    çļĦä¹IJ趣
    -0.07
    POSITIVE LOGITS
    æĬĬæĪij
    0.11
    ä¸ĬéŨ
    0.10
    å¿«é¤IJ
    0.09
    å®ĹæŨ
    0.09
    个æĢ§åĮĸ
    0.09
    串
    0.09
    Catch
    0.09
    å°±æĬĬ
    0.09
    stderr
    0.08
    社
    0.08
    Activations Density 0.006%

    No Known Activations