© 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. 18498
    Prev
    Next
    INDEX
    Explanations

    citations and journal titles

    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
    åĨ°åĨ·
    -0.10
    çĮľ
    -0.10
    è¿Ļå¥Ĺ
    -0.09
    lian
    -0.08
    æĭīèIJ¨
    -0.08
    çļĦä¸ĢäºĽ
    -0.08
    ç¬ĶèĢħ
    -0.08
    èĪįä¸įå¾Ĺ
    -0.08
    æ¹ĥ
    -0.08
    åħį
    -0.08
    POSITIVE LOGITS
    æļ¨
    0.10
    丢äºĨ
    0.09
    äºķ
    0.08
    во
    0.08
    ãĥĪãĥ¼
    0.08
    éĻ·éĺ±
    0.08
    owi
    0.08
    клÑİÑĩа
    0.08
    æľīåĬ©äºİ
    0.07
    éķ¿çŁŃ
    0.07
    Activations Density 0.239%

    No Known Activations