© 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. 34163
    Prev
    Next
    INDEX
    Explanations

    representatives

    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
    éģĹ产
    -0.09
    çĬĬ
    -0.09
    ä»»æķĻ
    -0.09
    æĩĴ
    -0.09
     Gan
    -0.09
    大å¥ĸ
    -0.08
    è°ĥåĬ¨
    -0.08
    æĹ¢æľī
    -0.08
    hero
    -0.08
    çķ¸å½¢
    -0.08
    POSITIVE LOGITS
    è´Łè´£äºº
    0.19
    å·¥ä½ľäººåijĺ
    0.18
    è´Łè´£åIJĮå¿Ĺ
    0.16
    人士
    0.14
    å®ĺåijĺ
    0.14
    管çIJĨ人åijĺ
    0.12
     officials
    0.12
    ä¸ĵ家
    0.12
    ä¸ļåĨħ人士
    0.11
     representatives
    0.10
    Activations Density 0.106%

    No Known Activations