© 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. 22464
    Prev
    Next
    INDEX
    Explanations

    transplant rejection

    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
    ly
    -0.12
    hift
    -0.11
    æ»ļæ»ļ
    -0.11
    åįģ足
    -0.10
    ness
    -0.10
    说æľį
    -0.10
    çŃĴ
    -0.10
    ä¸įæ¸ħ
    -0.09
    éĢģå¾Ģ
    -0.09
    ucks
    -0.09
    POSITIVE LOGITS
    ä½Ĩä»İ
    0.09
    èĭ´
    0.09
     ÑĩиÑģле
    0.09
    ä¸ĵåijĺ
    0.08
    ellen
    0.08
    еÑĨ
    0.08
     ÙĪجÙĩ
    0.08
    èį£èĢĢ
    0.08
    اج
    0.08
    ting
    0.08
    Activations Density 0.114%

    No Known Activations