© 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. 18624
    Prev
    Next
    INDEX
    Explanations

    asking for help or information

    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
    ç«ĭä½ĵ
    -0.09
    äºĮæīĭ
    -0.09
    åķ
    -0.09
    mand
    -0.09
    ç§ijæĻ®
    -0.09
     завод
    -0.09
    姿
    -0.09
    æĭ£
    -0.08
    å¹´èĸª
    -0.08
    å¾Īæ·±
    -0.08
    POSITIVE LOGITS
    åıįé¦Ī
    0.14
    .preview
    0.12
     feedback
    0.12
    preview
    0.11
     preview
    0.11
     Feedback
    0.11
    æĪIJåĵģ
    0.10
    _preview
    0.10
    Feedback
    0.10
    Preview
    0.10
    Activations Density 0.300%

    No Known Activations