© 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. 57462
    Prev
    Next
    INDEX
    Explanations

    in favor

    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
    èĪIJ
    -0.09
    robe
    -0.09
    è¡ĢèĦī
    -0.09
    ä½ĵéªĮ
    -0.09
    ân
    -0.09
    ç©¿æ¢Ń
    -0.09
    è·»
    -0.09
     Bip
    -0.09
    泪
    -0.09
     Pier
    -0.08
    POSITIVE LOGITS
     favor
    0.18
    favor
    0.17
    æľīåĪ©
    0.17
    ä¸įåĪ©
    0.15
     favorable
    0.15
     Favor
    0.14
     favour
    0.14
    æľīåĪ©äºİ
    0.13
    ç»ĻåĬĽ
    0.13
     favors
    0.13
    Activations Density 0.035%

    No Known Activations