© 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. 62171
    Prev
    Next
    INDEX
    Explanations

    in or on

    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
    ä½ľåĵģåĨħ容
    -0.10
    åħ¨éĿ¢èIJ½å®ŀ
    -0.10
    两èĢħ
    -0.10
    ä¸įæİĴéĻ¤
    -0.09
    俶
    -0.09
    æݧèĤ¡éĽĨåĽ¢
    -0.09
    æīįè¡Į
    -0.09
    ãģ¾ãģķ
    -0.09
    cing
    -0.09
    æ¶īå«Į
    -0.09
    POSITIVE LOGITS
     being
    0.09
    erre
    0.09
     Trap
    0.09
    edly
    0.08
    ANGER
    0.08
    ä¸Ģå¥Ĺ
    0.08
    xbb
    0.08
    海滨
    0.08
    eland
    0.08
    obl
    0.08
    Activations Density 0.018%

    No Known Activations