© 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. 33622
    Prev
    Next
    INDEX
    Explanations

    money, United States, Long, RUN

    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
    丸
    -0.10
     Relax
    -0.09
    ä¸Ģè´¯
    -0.09
    rng
    -0.09
    éģ
    -0.08
    紧紧
    -0.08
    ä¼°
    -0.08
    èĹ»
    -0.08
    åĨĮ
    -0.08
    çļĦæĥħ
    -0.08
    POSITIVE LOGITS
    åŀ«
    0.14
    èĩªè¡Į
    0.12
    èĩªä¸»åĪĽæĸ°
    0.11
    èĩªåıij
    0.11
     personally
    0.11
    åĩºèµĦ
    0.10
    æľ¬äºº
    0.10
    ä½łèĩªå·±
    0.10
    è´Łæĭħ
    0.10
    èĩªåĪĨãģ§
    0.10
    Activations Density 0.096%

    No Known Activations