© 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. 22822
    Prev
    Next
    INDEX
    Explanations

    numbers and page locations

    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
    anky
    -0.09
    èĩªèº«çļĦ
    -0.09
     PIE
    -0.08
    羡
    -0.08
    antan
    -0.08
    аÑĢа
    -0.08
    indy
    -0.08
    _UNS
    -0.08
    isty
    -0.08
    andler
    -0.08
    POSITIVE LOGITS
    第ä¸ī个
    0.11
    第ä¸ī代
    0.10
    éĩĮéĿ¢æľī
    0.10
    便ä¼ļ
    0.09
    å°¤åħ¶æĺ¯åľ¨
    0.09
    å¾Ģä¸Ĭ
    0.09
    åģľçķĻ
    0.09
    åħ¶ä¸Ńæľī
    0.09
    æĦ£
    0.09
    第ä¸ī
    0.08
    Activations Density 0.126%

    No Known Activations