© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37552
    Prev
    Next
    INDEX
    Explanations

    i 'm / i 'll / i 've

    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
    æĪijè§īå¾Ĺ
    -0.13
    æĪij认为
    -0.12
    æĪij们认为
    -0.11
    ä¸įäºĨ
    -0.11
    æĪijæĥ³
    -0.10
    æĪijä¸Ģ缴
    -0.10
    ä½łè§īå¾Ĺ
    -0.10
    å®ŀåľ¨
    -0.10
    æĪijå¸ĮæľĽ
    -0.09
    æĪijä¸įæĥ³
    -0.09
    POSITIVE LOGITS
    æİĮæı¡äºĨ
    0.10
    anders
    0.09
    æľīä¸įå°ij
    0.09
    ders
    0.09
    çŃīåĪ°
    0.09
    loth
    0.09
    åģļçļĦ
    0.08
    è£Ĩ
    0.08
    -Smith
    0.08
    AUD
    0.08
    Activations Density 0.043%

    No Known Activations