© 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. 1890
    Prev
    Next
    INDEX
    Explanations

    integrating and integrated concepts

    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
    æ¡İ
    -0.09
    ancell
    -0.08
    Å¡ÃŃ
    -0.08
    ä¸į论
    -0.08
    严
    -0.08
    ãn
    -0.08
    顺
    -0.08
    ubo
    -0.08
     tph
    -0.08
    oby
    -0.08
    POSITIVE LOGITS
    ä¸Ģä½ĵåĮĸ
    0.14
    éĽĨæĪIJ
    0.13
    âĪ«
    0.12
    æķ´åIJĪ
    0.12
     INTO
    0.12
    为ä¸Ģä½ĵ
    0.11
    ç»´å°Ķ
    0.10
    èŀįåħ¥
    0.10
    Into
    0.10
     Integrated
    0.10
    Activations Density 0.097%

    No Known Activations