© 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. 32084
    Prev
    Next
    INDEX
    Explanations

    street names and addresses

    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
    agi
    -0.09
    æģª
    -0.08
    æ´ŀ
    -0.08
    å¤ļä¹ħ
    -0.08
    ãĥĢãĥ³
    -0.08
    WARD
    -0.08
    zik
    -0.08
    /documentation
    -0.08
    _TRAN
    -0.08
    -flex
    -0.08
    POSITIVE LOGITS
    ä¸ĭæīĭ
    0.09
    éĤĽ
    0.09
    å°±æĥ³
    0.09
    大åħ¨
    0.09
    æĸĩåĮĸ产ä¸ļ
    0.09
    à¹ģห
    0.09
    åĪĨæѧ
    0.09
    è¾Ľèĭ¦
    0.08
    atab
    0.08
    å¼Ģå¿ĥ
    0.08
    Activations Density 0.055%

    No Known Activations