© 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. 5587
    Prev
    Next
    INDEX
    Explanations

    adenosine and nucleosides

    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
    å¾®åķĨ
    -0.09
    æĮģ
    -0.09
    梳
    -0.09
    åľ¨çº¿åĴ¨è¯¢
    -0.09
    éľ²å¤©
    -0.08
    å¼ĺæī¬
    -0.08
    æ·ij
    -0.08
    ç«ŀäºīä¼ĺåĬ¿
    -0.08
    諮詢
    -0.08
    è£Ł
    -0.08
    POSITIVE LOGITS
    phis
    0.11
    ãĥ¼ãĥł
    0.10
     oblig
    0.09
    ä¸ĵ线
    0.09
    ename
    0.08
    ç¿»
    0.08
    ----------------------------------------------------------------------
    0.08
    สะ
    0.08
    acional
    0.08
    èĬĴ
    0.08
    Activations Density 0.138%

    No Known Activations