© 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. 56924
    Prev
    Next
    INDEX
    Explanations

    saving throw, opening, root

    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
    åı¦ä¸ĢåįĬ
    -0.10
    AML
    -0.10
    æĬ½
    -0.10
    æĬĸ
    -0.10
    æ±Łæ¹ĸ
    -0.09
    æĿ¡ä¾ĭ
    -0.09
    æ³ķ令
    -0.09
    amac
    -0.09
    roma
    -0.09
    pll
    -0.09
    POSITIVE LOGITS
    足足
    0.10
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    0.09
    俺
    0.09
    çĿ
    0.09
    ç©´
    0.08
     POW
    0.08
    æĪ´ä¸Ĭ
    0.08
    zap
    0.08
    çļĦéĤ£ä¸Ģ
    0.08
    èĢģåŃIJ
    0.08
    Activations Density 0.069%

    No Known Activations