© 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. 32499
    Prev
    Next
    INDEX
    Explanations

    beginner-friendly

    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
    累累
    -0.09
    åįĥåı¤
    -0.09
    orical
    -0.09
    åıijå±ķä¸Ń
    -0.08
    åѤåĦ¿
    -0.08
    åīį身
    -0.08
    pping
    -0.08
     Ñĩего
    -0.08
    鼾
    -0.08
    ä¸įä¸ĭ
    -0.08
    POSITIVE LOGITS
    è°Ł
    0.11
    æĢ»è§īå¾Ĺ
    0.10
    sert
    0.10
    sWith
    0.10
    -friendly
    0.10
    tons
    0.10
    iate
    0.09
    çĶļèĩ³æĺ¯
    0.09
    ä¹ĭä½ľ
    0.09
    iates
    0.09
    Activations Density 0.014%

    No Known Activations