© 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. 27879
    Prev
    Next
    INDEX
    Explanations

    guessing questions or quizzes

    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
    æIJŀ好
    -0.10
    oric
    -0.09
    主
    -0.09
    iskey
    -0.09
    磨
    -0.08
    åĬŀäºĭ
    -0.08
    æİ¥è¿ij
    -0.08
    èĿ¶
    -0.08
    æij©æĵ¦
    -0.08
    éal
    -0.08
    POSITIVE LOGITS
    æĺ¯ä»Ģä¹Īåij¢
    0.14
    è°ľ
    0.12
     дог
    0.11
    åĪ°åºķ
    0.11
    hint
    0.10
    æĤĦæĤĦ
    0.10
    è°ģèĥ½
    0.10
    究竣
    0.10
    çĮľ
    0.10
    ä¸ī人
    0.10
    Activations Density 0.079%

    No Known Activations