© 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. 39566
    Prev
    Next
    INDEX
    Explanations

    talk about

    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
    /from
    -0.13
    åŀĤ
    -0.09
    /out
    -0.09
    /on
    -0.09
     chiếu
    -0.09
    /disable
    -0.09
    æ°ijæĶ¿å±Ģ
    -0.09
    èĭ¦èĭ¦
    -0.09
    /of
    -0.09
    forth
    -0.09
    POSITIVE LOGITS
    íģIJ
    0.09
     about
    0.09
    uate
    0.09
    ÙĪا
    0.09
    rolling
    0.09
    procs
    0.09
    ÑĢен
    0.09
    åºĶæĢ¥ç®¡çIJĨ
    0.08
    /set
    0.08
     далÑĮÑĪе
    0.08
    Activations Density 0.013%

    No Known Activations