© 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. 56616
    Prev
    Next
    INDEX
    Explanations

    git, wiki, trial

    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
    èķĪ
    -0.11
    æĭ©
    -0.11
    å¡Į
    -0.10
    çīĪæĿĥå½ĴåİŁ
    -0.10
    iya
    -0.10
    é¢ĩ
    -0.10
    åľ¨ä¸Ģ个
    -0.10
    æīģ
    -0.09
    深交
    -0.09
    èµ°å¾Ĺ
    -0.09
    POSITIVE LOGITS
    å¸ĥç½®
    0.08
    è°Ĺ
    0.08
     tri
    0.08
     shielding
    0.08
     hang
    0.08
    åĴ¸
    0.08
    .ne
    0.08
    ined
    0.08
    åī¯
    0.08
     holding
    0.07
    Activations Density 0.084%

    No Known Activations