© 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. 54807
    Prev
    Next
    INDEX
    Explanations

    got a / to

    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
    /or
    -0.11
    æŶè£ħ
    -0.09
    çĮĿ
    -0.09
    æĬ¥è®°èĢħ
    -0.09
    æľīæĽ´å¥½çļĦ
    -0.09
    èĢĦ
    -0.09
    ç¼ĺåĪĨ
    -0.09
    ä¸įå·²
    -0.09
    ä¾Ħ
    -0.08
    esco
    -0.08
    POSITIVE LOGITS
    tings
    0.13
    ting
    0.12
    aneous
    0.10
    çĦ¶æĺ¯
    0.10
    emean
    0.10
    timeofday
    0.10
    chas
    0.10
    ters
    0.09
    ness
    0.09
    ton
    0.09
    Activations Density 0.015%

    No Known Activations