© 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. 47706
    Prev
    Next
    INDEX
    Explanations

    what kind

    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
    æľīå¤ļå°ij
    -0.11
    è¿Ļç§įæĥħåĨµ
    -0.10
    æľīåĵªäºĽ
    -0.10
    ä¼ļå±ķ
    -0.09
    åı¯èĥ½åĩºçİ°
    -0.09
    åºĶåľ¨
    -0.09
    å¥Ĥ
    -0.08
     söz
    -0.08
    åIJĦè¡Į
    -0.08
    imei
    -0.08
    POSITIVE LOGITS
    æĥ³èµ·æĿ¥
    0.10
    /lg
    0.09
    bury
    0.09
    æIJĶ
    0.09
    åŀĴ
    0.09
    æĸ¹å¼ıè¿Ľè¡Į
    0.09
    对åħ¶è¿Ľè¡Į
    0.08
    æĿĤå¿Ĺ
    0.08
    æĪijçĽ¸ä¿¡
    0.08
    ÙĦÙĦ
    0.08
    Activations Density 0.055%

    No Known Activations