© 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. 2861
    Prev
    Next
    INDEX
    Explanations

    file names and code components

    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
    ãĤ¢ãĥ¡ãĥª
    -0.09
    ãĤ¨ãĥįãĥ«
    -0.09
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    ãĤ¿ãĤ¤ãĥŁ
    -0.09
    ãĤ¤ãĥ³ãĤ¿ãĥ¼ãĥį
    -0.09
    ãĤ±ãĥ¼ãĤ
    -0.09
    ãĤŃãĥ£ãĥ³ãĥļ
    -0.08
    ãĤ¢ãĤ¤ãĥĨ
    -0.08
    ãĥĽãĥĨ
    -0.08
    ãĥ¡ãĥ¼ãĤ
    -0.08
    POSITIVE LOGITS
    ä¹Łä¸įä¾ĭå¤ĸ
    0.12
    以ä¸ĭç®Ģ称
    0.09
    æŃ¤ä¸¾
    0.09
    ä¸ĭéĿ¢å°±
    0.09
    ä¸įéĹ´
    0.09
    iegel
    0.09
    毫æĹłçĸij
    0.09
    ì¹Ļ
    0.08
    ä¹Łæĺ¯å¦ĤæѤ
    0.08
    UnderTest
    0.08
    Activations Density 17.297%

    No Known Activations