© 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. 5710
    Prev
    Next
    INDEX
    Explanations

    often followed by a descriptor

    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
    æĪIJç«ĭ以æĿ¥
    -0.12
    佬
    -0.10
    å§ĭç»Īä¿ĿæĮģ
    -0.10
    æѤå¤ĸ
    -0.09
    fty
    -0.09
    ç»Ī究
    -0.09
    常ãģ«
    -0.08
    æ¡ĥ
    -0.08
     поÑģÑĤоÑıнно
    -0.08
    son
    -0.08
    POSITIVE LOGITS
     xuyên
    0.19
    -times
    0.15
    entimes
    0.12
    -used
    0.12
    çĹĩ
    0.11
     times
    0.11
    IZER
    0.11
    /all
    0.11
    Times
    0.11
    (times
    0.11
    Activations Density 0.037%

    No Known Activations