© 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. 33674
    Prev
    Next
    INDEX
    Explanations

    system call, system detect, system automatically, System.Drawing

    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
    ç¥Ģ
    -0.10
    ech
    -0.09
    æŁIJ个
    -0.09
    æ´»çĿĢ
    -0.09
    çī¦
    -0.09
    èĩ§
    -0.08
    å£ķ
    -0.08
    è°¯
    -0.08
     dime
    -0.08
    ä¸ĢæĬĬ
    -0.08
    POSITIVE LOGITS
    ç¿ģ
    0.09
     pit
    0.09
    owy
    0.09
    çļĦæ¶Īæģ¯
    0.09
    pired
    0.09
    娥
    0.08
    edata
    0.08
    ãĤĪãģĨãģª
    0.08
    ä½İæĪIJæľ¬
    0.08
    æī¯
    0.08
    Activations Density 0.001%

    No Known Activations