© 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. 61774
    Prev
    Next
    INDEX
    Explanations

    simple, simpler, simplest, complexity

    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
    墨
    -0.10
    æĴĩ
    -0.09
    urous
    -0.09
    ouri
    -0.09
    ä¸įåĩº
    -0.08
    uro
    -0.08
    gings
    -0.08
    ä¸įä¸ĭ
    -0.08
    éĢĴ交
    -0.08
    åŁ´
    -0.08
    POSITIVE LOGITS
    ç®ĢåĮĸ
    0.15
    ç®Ģæ´ģ
    0.13
     simplicity
    0.13
    ç®Ģæĺĵ
    0.12
    (simp
    0.12
    å¤įæĿĤ
    0.11
    ãĤ·ãĥ³ãĥĹãĥ«
    0.11
    å¤įæĿĤçļĦ
    0.11
     complexity
    0.11
     Complexity
    0.10
    Activations Density 0.081%

    No Known Activations