© 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. 27388
    Prev
    Next
    INDEX
    Explanations

    overall goal

    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
    ema
    -0.10
    ÑĢей
    -0.09
    fully
    -0.09
    svc
    -0.09
    /th
    -0.09
    ãĤī
    -0.09
    ormal
    -0.09
    asher
    -0.08
    URT
    -0.08
    æ·ŀ
    -0.08
    POSITIVE LOGITS
    mente
    0.11
    -purpose
    0.10
    缮çļĦæĺ¯
    0.10
    Spoiler
    0.09
    ìĭ¸
    0.09
     Winner
    0.09
    most
    0.09
    è¿ĺä¸į
    0.09
    大å±Ģ
    0.09
    igator
    0.09
    Activations Density 0.034%

    No Known Activations