© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 30911
    Prev
    Next
    INDEX
    Explanations

    email addresses

    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
    è¿Ļæł·æīįèĥ½
    -0.10
    åīįè¿°
    -0.09
    ä¸ŃåĽ½åζéĢł
    -0.09
    éļ¶å±ŀäºİ
    -0.08
    åIJijçĿĢ
    -0.08
    ä½Ĩä¸įéĻIJ
    -0.08
    å°±è¡ĮäºĨ
    -0.08
    æŃ¤åIJİ
    -0.08
    ç»Ģ
    -0.08
    aÅĤ
    -0.08
    POSITIVE LOGITS
    insic
    0.09
    ä¸įå¾Ĺä¸į说
    0.09
    ä¸ī天
    0.08
    æĴķ
    0.08
    çļĦç¡®
    0.08
    è²ī
    0.08
    arest
    0.08
    lij
    0.08
    è£
    0.08
    apas
    0.08
    Activations Density 0.127%

    No Known Activations