© 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. 3407
    Prev
    Next
    INDEX
    Explanations

    one over another

    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
    åľ¨åIJĮä¸Ģ
    -0.08
    æĬĬè¿ĻäºĽ
    -0.08
    棣
    -0.08
    umph
    -0.08
    ci
    -0.08
    eln
    -0.08
    ment
    -0.08
    åĬłå¿«å»ºè®¾
    -0.08
    åĴĮ个人
    -0.08
    ands
    -0.08
    POSITIVE LOGITS
    åı¦ä¸Ģ
    0.18
    åı¦ä¸Ģ个
    0.18
    åı¦ä¸Ģè¾¹
    0.16
    åı¦å¤ĸä¸Ģ个
    0.16
    åı¦ä¸Ģç§į
    0.15
     дÑĢÑĥг
    0.15
     another
    0.14
    åı¦ä¸Ģä½į
    0.14
     дÑĢÑĥгой
    0.14
    åı¦ä¸Ģæĸ¹éĿ¢
    0.13
    Activations Density 0.088%

    No Known Activations