© 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. 5043
    Prev
    Next
    INDEX
    Explanations

    or and

    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
    otti
    -0.09
    sem
    -0.08
    asin
    -0.08
    æľºç»Ħ
    -0.08
    æł¹æį®èĩªå·±
    -0.08
    illy
    -0.07
    éĿ¡
    -0.07
    èļ±
    -0.07
    amer
    -0.07
    ta
    -0.07
    POSITIVE LOGITS
    åĨį说
    0.11
    çģ«æĺŁ
    0.11
     ÙĤائ
    0.10
     thuáºŃt
    0.10
    Opera
    0.09
    楼ä¸Ĭ
    0.09
    ëī´ìĬ¤
    0.09
    诣
    0.09
     Fare
    0.09
    æݥ触
    0.09
    Activations Density 0.006%

    No Known Activations