© 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. 1967
    Prev
    Next
    INDEX
    Explanations

    revision before publication

    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
    æĮ¤
    -0.09
    emme
    -0.09
    çıŃ
    -0.09
    ormap
    -0.08
    è¸ıå®ŀ
    -0.08
    æľīåIJį
    -0.08
    åĪ»
    -0.08
    è¸Į
    -0.08
    INDER
    -0.08
    nova
    -0.08
    POSITIVE LOGITS
    仲
    0.10
    åĢļ
    0.10
    ubb
    0.09
    纷纷表示
    0.08
    ä¸ķ
    0.08
    è§Ĵ度æĿ¥çľĭ
    0.08
    ä¸İæĹ¶ä¿±è¿Ľ
    0.08
    èĥ¶
    0.08
    æģķ
    0.08
    ulta
    0.08
    Activations Density 0.011%

    No Known Activations