© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53196
    Prev
    Next
    INDEX
    Explanations

    itself, themselves, board, controller

    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
    sı
    -0.09
    ä¾į
    -0.08
    TOTAL
    -0.08
     Vital
    -0.08
    æĪĸèĢħåħ¶ä»ĸ
    -0.08
     mun
    -0.08
    çĶļèĩ³æĺ¯
    -0.08
    addle
    -0.08
    éĿŀçī©è´¨
    -0.08
    è¿Ļä¹Īåģļ
    -0.08
    POSITIVE LOGITS
    æľ¬èº«çļĦ
    0.25
    æľ¬èº«
    0.25
     itself
    0.22
     ÑģобÑģÑĤвенно
    0.18
    èĩªèº«
    0.16
    èĩªèº«çļĦ
    0.15
     ìŀIJì²´
    0.13
    æľ¬äºº
    0.13
    主ä½ĵ
    0.12
    æľ¬èº«å°±
    0.12
    Activations Density 0.718%

    No Known Activations