© 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. 6437
    Prev
    Next
    INDEX
    Explanations

    tools, equipment, and prices

    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
    éĻĽä¸ĭ
    -0.09
    LOSE
    -0.09
    åįĩåѦ
    -0.09
    åľ¨è¿ĩ渡
    -0.09
    é¾Ľ
    -0.09
    Prev
    -0.08
    uant
    -0.08
     nâng
    -0.08
    compass
    -0.08
    èĮļ
    -0.08
    POSITIVE LOGITS
    å¹´æĬ¥
    0.09
     cord
    0.09
     Cord
    0.09
    cord
    0.08
    è½»
    0.08
     Seymour
    0.08
    æīĭæĮģ
    0.08
    OURCE
    0.08
    _invoke
    0.08
    髹
    0.08
    Activations Density 0.110%

    No Known Activations