© 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. 61650
    Prev
    Next
    INDEX
    Explanations

    on behalf

    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
    pond
    -0.09
    éĵŃ
    -0.09
    çİ©æ³ķ
    -0.09
    åĪĴ
    -0.09
    è¿Ļä¸Ģ次
    -0.09
    owler
    -0.08
    è¿Ŀæ³ķ
    -0.08
    举æĸ¹
    -0.08
    ods
    -0.08
    oplay
    -0.08
    POSITIVE LOGITS
     behalf
    0.24
    代è¨Ģ
    0.12
    为代表
    0.12
    æĽ¿
    0.11
    代
    0.11
    ä»£æĽ¿
    0.10
    代表
    0.10
    anked
    0.10
    为æĪij们
    0.10
    åŁºç¡Ģä¸Ĭ
    0.09
    Activations Density 0.056%

    No Known Activations