© 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. 48322
    Prev
    Next
    INDEX
    Explanations

    protein binding and coupling

    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
    èĶļ
    -0.10
    å¹ķ
    -0.09
    å²Ń
    -0.09
    ä¸įæĪIJ
    -0.09
    éķ¿çŁŃ
    -0.09
    æ¹į
    -0.09
    PFN
    -0.08
    æĪ·åı£
    -0.08
    å®ģ
    -0.08
    çī¹äº§
    -0.08
    POSITIVE LOGITS
    æĭ¢
    0.11
    Crow
    0.10
     crown
    0.10
    æļ´
    0.10
     crow
    0.10
    ä¿Ŀå§Ĩ
    0.10
    æĭ®
    0.09
    满满
    0.09
    æijĨ
    0.09
    _states
    0.09
    Activations Density 0.481%

    No Known Activations