© 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. 26703
    Prev
    Next
    INDEX
    Explanations

    you and us offer

    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
    åĹij
    -0.12
    è¿Ļ家åħ¬åı¸
    -0.11
    ç¦
    -0.10
    让æ¶Īè´¹èĢħ
    -0.10
    æĪIJ绩
    -0.10
    çļĦæĪIJ绩
    -0.09
    æ·®åįĹ
    -0.09
    çķ´
    -0.09
    ç¬ijè¯Ŀ
    -0.09
    å°ıçĶ·åŃ©
    -0.09
    POSITIVE LOGITS
    igner
    0.08
    å¨
    0.08
    åİĮ
    0.08
    asia
    0.08
    erner
    0.08
    éĻIJ度
    0.08
    (proto
    0.07
    æ³¢
    0.07
    ially
    0.07
    quare
    0.07
    Activations Density 0.042%

    No Known Activations