© 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. 34861
    Prev
    Next
    INDEX
    Explanations

    legs and rest

    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
    çĤĬ
    -0.09
    delegate
    -0.09
    hei
    -0.09
    akens
    -0.08
    åħ¬ç¤¾
    -0.08
     delegate
    -0.08
    usher
    -0.08
    à¸Ńà¸Ńà¸Ļ
    -0.08
    å¤įåħ´
    -0.08
    ymi
    -0.08
    POSITIVE LOGITS
     ног
    0.13
    èĦļ
    0.11
    ä¸įä¿¡
    0.10
    osit
    0.10
    åĿIJçĿĢ
    0.09
    _Impl
    0.09
    åĬ¼
    0.09
    å±Ī
    0.09
    çļĦå°ı
    0.09
    蹬
    0.08
    Activations Density 0.027%

    No Known Activations