© 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. 38661
    Prev
    Next
    INDEX
    Explanations

    expensive, costly

    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
    èĤ¯å®ļä¼ļ
    -0.09
    oks
    -0.09
    èĢĮéĿŀ
    -0.09
    åı¯ä»¥è¯´æĺ¯
    -0.09
    addock
    -0.09
    æļ
    -0.08
    æŀĦ件
    -0.08
    outs
    -0.08
    olk
    -0.08
    ieres
    -0.08
    POSITIVE LOGITS
    ä¸įå¿ħè¦ģçļĦ
    0.11
    èIJĿ
    0.10
    åį´åıijçİ°
    0.09
    subclass
    0.09
    phin
    0.09
     nor
    0.09
    ä¸Ģæł·çļĦ
    0.09
     Oval
    0.09
    cool
    0.08
    adesh
    0.08
    Activations Density 0.102%

    No Known Activations