© 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. 58907
    Prev
    Next
    INDEX
    Explanations

    phrases ending in period, question mark, or bang

    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
    ä¹ŁæŃ£æĺ¯
    -0.09
    ä¸įè¦ģåĨį
    -0.09
    éĤĪ
    -0.08
    çļĦæ¯į亲
    -0.08
    ä¸įèµ·
    -0.08
    éĩijèī²
    -0.08
    acid
    -0.08
    éĥ½ä¸įä¼ļ
    -0.08
    OSH
    -0.08
    没æľīåĬŀæ³ķ
    -0.08
    POSITIVE LOGITS
    èĢĮæĺ¯
    0.11
    缸åıį
    0.10
    大éĺŁ
    0.10
    ãģŀ
    0.09
    为é¦ĸ
    0.09
    æĩĭ
    0.09
    tre
    0.09
    å¼ºåĽ½
    0.09
    ogle
    0.09
    pri
    0.09
    Activations Density 0.093%

    No Known Activations