© 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. 35472
    Prev
    Next
    INDEX
    Explanations

    compared to or contrasted with

    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
    ç®±åŃIJ
    -0.10
    é¤IJæ¡Į
    -0.10
    éĿĵ
    -0.09
    åħħåĪĨ
    -0.09
    _TestCase
    -0.09
    社ä¼ļåĮĸ
    -0.09
    å©Ĩ
    -0.09
    aggi
    -0.09
    èĤĮèĤ¤
    -0.09
    precation
    -0.08
    POSITIVE LOGITS
    åīįè¾Ī
    0.10
    对çħ§
    0.10
    ç®Ĺ
    0.09
    existing
    0.09
     existing
    0.09
    æĮģå¹³
    0.09
    ä¸įä½İäºİ
    0.09
    ç¿»
    0.08
    æĭ¿äºĨ
    0.08
    æĹłç¼ĺ
    0.08
    Activations Density 0.275%

    No Known Activations