© 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. 49751
    Prev
    Next
    INDEX
    Explanations

    and followed by noun

    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
    åĽ¢
    -0.09
     eve
    -0.09
    çļĦ女åĦ¿
    -0.09
    çļĦåĦ¿åŃIJ
    -0.09
     Tour
    -0.09
    第ä¸Ģ次
    -0.09
    .SQL
    -0.08
    ucky
    -0.08
    icken
    -0.08
    纺ç»ĩ
    -0.08
    POSITIVE LOGITS
    greens
    0.11
    俱
    0.11
    ä¸įåIJĪçIJĨ
    0.10
     alike
    0.10
    ä¸Ĭä¸ĭ游
    0.10
    Õ»
    0.10
    åĬ³åĬ¡æ´¾éģ£
    0.10
    ä¸Ĭä¸ĭ
    0.10
    两èĢħ
    0.09
    .LENGTH
    0.09
    Activations Density 0.126%

    No Known Activations