© 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. 17006
    Prev
    Next
    INDEX
    Explanations

    ages under a certain number

    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
    ä¸įæĢķ
    -0.11
    (Fl
    -0.10
    å®ŀäºĭæ±Ĥæĺ¯
    -0.10
    èIJ§
    -0.09
    马ä¸Ĭå°±
    -0.09
    äºĮåŃĹ
    -0.09
    åģ¥åº·çļĦ
    -0.08
    моÑĤ
    -0.08
    loy
    -0.08
    åįĹæµ·
    -0.08
    POSITIVE LOGITS
    erland
    0.09
    为ä¸Ńå¿ĥ
    0.09
    ÑĢеги
    0.09
    ооÑĢ
    0.08
    edly
    0.08
     Chad
    0.08
    æĭīæĸ¯
    0.08
    .Alignment
    0.08
    _Framework
    0.08
     Monster
    0.08
    Activations Density 0.065%

    No Known Activations