© 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. 4914
    Prev
    Next
    INDEX
    Explanations

    Eaton, Bowie, ON

    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
    天ä¸Ĭ
    -0.09
    мÑı
    -0.09
    è´¯
    -0.09
    骨
    -0.08
    esco
    -0.08
    éĺĹ
    -0.08
    æ±Ľ
    -0.08
    x
    -0.08
    æŀī
    -0.08
    irection
    -0.08
    POSITIVE LOGITS
    ehler
    0.10
    arda
    0.09
    olle
    0.09
    äºĭåĬ¡
    0.09
    FER
    0.09
    reur
    0.08
    æ±
    0.08
    æĹİ
    0.08
    .Transaction
    0.08
    åªļ
    0.08
    Activations Density 0.018%

    No Known Activations