© 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. 1514
    Prev
    Next
    INDEX
    Explanations

    These followed by noun

    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
    åĵģçīĮçļĦ
    -0.10
    æĸ¹å¼ıè¿Ľè¡Į
    -0.10
    /vnd
    -0.09
    æ¶Ŀ
    -0.09
    躲
    -0.09
    è¿Ļæł·ä¸Ģ个
    -0.09
     ÑĤоÑĢ
    -0.09
    çļĦæĸ¹å¼ıæĿ¥
    -0.09
    åĵģçīĮ
    -0.08
    dk
    -0.08
    POSITIVE LOGITS
    缴æݥ影åĵį
    0.09
    å¾Īå¿«
    0.09
    éĢĤçĶ¨äºİ
    0.09
    ä¹ŁåĽłæѤ
    0.09
    大å¤ļ
    0.09
     are
    0.09
    ickers
    0.08
    åįģåĩłå¹´
    0.08
    tek
    0.08
    æĮģæľī
    0.08
    Activations Density 0.062%

    No Known Activations