© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36834
    Prev
    Next
    INDEX
    Explanations

    Hockenheim, Grand Prix

    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
    çļĦåĪ©çĽĬ
    -0.10
    .dx
    -0.09
    éĻ¤å°ĺ
    -0.09
    æºľ
    -0.08
    æĺ¾çİ°
    -0.08
    uye
    -0.08
    builtin
    -0.08
    å®ķ
    -0.08
    ilmiÅŁ
    -0.08
    olini
    -0.08
    POSITIVE LOGITS
    æĢ»æľī
    0.09
    веÑģ
    0.08
    etto
    0.08
    avit
    0.08
    belt
    0.08
    è¡
    0.08
    æĬĹæĭĴ
    0.08
    ÙħÙĤ
    0.08
    女æĢ§æľĭåıĭ
    0.08
    Scheme
    0.08
    Activations Density 0.002%

    No Known Activations