© 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. 3738
    Prev
    Next
    INDEX
    Explanations

    display scrolling matrix

    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
     archetype
    -0.09
    åľ¨ç¾İåĽ½
    -0.09
    ìĤ¬ë¥¼
    -0.09
    ç½ij讯
    -0.09
     bows
    -0.08
     бÑĥм
    -0.08
    ç½ijéĢļ
    -0.08
    ách
    -0.08
    PIO
    -0.08
    Blueprint
    -0.08
    POSITIVE LOGITS
    æ°¸ä¸į
    0.10
    ä¸ĢæŶ
    0.09
    æ¯ĶåĪĨ
    0.09
    æĻļ
    0.09
    尾巴
    0.09
    åĿĬ
    0.09
     Gael
    0.08
    çĶŃ
    0.08
     ais
    0.08
    gett
    0.08
    Activations Density 0.128%

    No Known Activations