© 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. 32188
    Prev
    Next
    INDEX
    Explanations

    Cite as, State

    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
    赤
    -0.09
    庶
    -0.09
    å°±æĦıåij³çĿĢ
    -0.09
    åł¡
    -0.09
    çĴŀ
    -0.09
    ä¸įä¸ĭ
    -0.09
    æ¿ĢçĥĪçļĦ
    -0.09
    è§ĴéĢIJ
    -0.08
    æĸĻçIJĨ
    -0.08
    POSITIVE LOGITS
    æľīåIJį
    0.10
    _languages
    0.09
    伶
    0.08
    atte
    0.08
    bias
    0.08
     Prepared
    0.08
    áĢĩ
    0.08
     Bias
    0.08
     quake
    0.08
    æĹłå¿§
    0.07
    Activations Density 0.067%

    No Known Activations