© 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. 61905
    Prev
    Next
    INDEX
    Explanations

    great good extremely

    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
    gars
    -0.08
    å®īåħ¨ä¿Ŀéļľ
    -0.08
    zym
    -0.08
    èĪįä¸įå¾Ĺ
    -0.08
    istrate
    -0.07
    ctest
    -0.07
    ULE
    -0.07
    亥
    -0.07
    chet
    -0.07
    è½®
    -0.07
    POSITIVE LOGITS
    ç¿ĺ
    0.11
    èĢĮçİ°åľ¨
    0.11
    梦è§ģ
    0.10
    éķ°
    0.10
    åIJĦè¡Į
    0.09
    èĤłèĥĥ
    0.09
    ìĸ¸
    0.09
    æĺĤ
    0.09
    æĸ°æµªå¾®åįļ
    0.09
    åĩłä¸ªäºº
    0.09
    Activations Density 0.062%

    No Known Activations