© 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. 38064
    Prev
    Next
    INDEX
    Explanations

    filed complaints and trials

    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
    IRM
    -0.09
    æĿŀ
    -0.08
    è´ŀ
    -0.08
     Kerry
    -0.08
    Craig
    -0.08
     moll
    -0.08
    ipp
    -0.08
     Craig
    -0.08
    误
    -0.08
    udu
    -0.07
    POSITIVE LOGITS
    éķ¿å¤§äºĨ
    0.08
    æĦ£
    0.08
    æĮĩ示
    0.08
    æīĭæ³ķ
    0.08
    éĵº
    0.08
     indicted
    0.08
    rides
    0.08
    æѤæ¡Ī
    0.08
    prech
    0.08
    è¡Įç¨ĭ
    0.08
    Activations Density 0.077%

    No Known Activations