© 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. 29858
    Prev
    Next
    INDEX
    Explanations

    approaching or arriving soon

    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
    ç¼ĺ
    -0.09
    endir
    -0.09
    çļĦæ¯į亲
    -0.09
    angu
    -0.09
     Ñ
    -0.09
    æĺ³
    -0.09
    ingo
    -0.08
    汤
    -0.08
    åĤ²
    -0.08
    iske
    -0.08
    POSITIVE LOGITS
    ä¹ĭåĬ¿
    0.09
    æĦĪåĬł
    0.08
    æĦĪ
    0.08
    zik
    0.08
    è¯ķçĤ¹å·¥ä½ľ
    0.08
     vest
    0.08
    minent
    0.08
    ãģľ
    0.08
    æĿ¥ä¸´
    0.08
     Hutch
    0.08
    Activations Density 0.034%

    No Known Activations