© 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. 4532
    Prev
    Next
    INDEX
    Explanations

    recent advances and progress

    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
    åĽ½ãģ®
    -0.10
    èµŀ
    -0.10
    亶
    -0.09
    é¢Ĥ
    -0.09
    pred
    -0.08
    obot
    -0.08
    æĬ¥ä¸ļ
    -0.08
    责任人
    -0.08
    æĪĺèĥľ
    -0.08
    åĨ°åĨ·
    -0.08
    POSITIVE LOGITS
     developments
    0.11
    uses
    0.10
    è¶ĭåĬ¿
    0.10
    æľīç§į
    0.10
    è¿Ľå±ķ
    0.10
    ommen
    0.09
     trends
    0.09
    æ¼ĶæĬĢ
    0.09
    ç¢į
    0.09
    åıªèĥ½è¯´
    0.09
    Activations Density 0.266%

    No Known Activations