© 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. 11097
    Prev
    Next
    INDEX
    Explanations

    orthopedic and ocular implants

    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
    ç£ķ
    -0.10
    fir
    -0.09
    西åįĹ
    -0.09
     обла
    -0.09
     Spot
    -0.08
    åıįæŃ£
    -0.08
    çŃ¾ç½²
    -0.08
    립
    -0.08
    åIJĪåIJĮ
    -0.08
     virtue
    -0.08
    POSITIVE LOGITS
    æĿIJè´¨
    0.11
    htt
    0.10
    档次
    0.09
    kker
    0.09
    æ¤įåħ¥
    0.09
    ht
    0.09
    çķĻåľ¨
    0.09
    èĩªåĬ©
    0.09
    iginal
    0.09
    esson
    0.09
    Activations Density 0.241%

    No Known Activations