© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60944
    Prev
    Next
    INDEX
    Explanations

    established, available, passed, started

    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
    posable
    -0.08
    ä¼ģä¸ļåĴĮ
    -0.08
    è¡ĮåĪĹ
    -0.08
    ifest
    -0.07
    ä¸ĵ项è¡ĮåĬ¨
    -0.07
    对ä»ĸ们
    -0.07
    ä¹ĥ
    -0.07
     very
    -0.07
    éģĤ
    -0.07
    å¾Īä½İ
    -0.07
    POSITIVE LOGITS
    iming
    0.10
    æ¸ħæĻ°
    0.10
    hani
    0.09
    åī¯
    0.09
    _CLEAR
    0.09
    æ¸ħæ¥ļ
    0.09
    æĶ¯
    0.09
    ided
    0.09
    gis
    0.09
    azed
    0.08
    Activations Density 0.417%

    No Known Activations