© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51313
    Prev
    Next
    INDEX
    Explanations

    victory or loss

    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
    å¼ķãģį
    -0.10
    饼
    -0.10
    ç«ŀäºīåĬĽ
    -0.09
    éĶ°
    -0.09
    骨
    -0.09
    adir
    -0.08
    IJľ
    -0.08
    æĶ¾æĺł
    -0.08
    ä½ĵåĪ¶æĶ¹éĿ©
    -0.08
    å¾ĺå¾Ĭ
    -0.08
    POSITIVE LOGITS
     victories
    0.12
    æĮ«æĬĺ
    0.10
    éĺ¶æ®µæĢ§
    0.10
     побед
    0.10
    æ¥ŀ
    0.10
     successes
    0.09
     victory
    0.09
    æĮ«
    0.09
    åķĥ
    0.09
    rz
    0.09
    Activations Density 0.039%

    No Known Activations