© 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. 31564
    Prev
    Next
    INDEX
    Explanations

    age or time

    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
    PropertyParams
    -0.09
    åħľ
    -0.09
    æĿł
    -0.09
    æ³IJ
    -0.08
    移åĬ¨ç«¯
    -0.08
    移åĬ¨
    -0.08
    Ñıз
    -0.08
     Ñģвое
    -0.08
    éĨµ
    -0.08
    èµłéĢģ
    -0.08
    POSITIVE LOGITS
    åĴİ
    0.10
    æĹ¶æľŁ
    0.10
    gli
    0.10
    ä»»ä½ķæŶåĢĻ
    0.09
    ез
    0.09
     slim
    0.09
    èĸħ
    0.09
    éĻĤ
    0.09
    onto
    0.09
    ä¸į好
    0.09
    Activations Density 0.012%

    No Known Activations