© 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. 55474
    Prev
    Next
    INDEX
    Explanations

    Stanley Cup or names

    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
    è´Ń
    -0.09
    æ¤ĭ
    -0.08
    folio
    -0.08
    æīĵåĬ¨
    -0.08
    åĬłåĢį
    -0.08
    æŁ°
    -0.08
    就没
    -0.08
     Cele
    -0.08
     sca
    -0.08
    èĸª
    -0.07
    POSITIVE LOGITS
    UR
    0.09
    린
    0.09
    kel
    0.09
    æŀ¯
    0.09
    çªĿ
    0.08
    uÃŃ
    0.08
    æݬ
    0.08
     Wired
    0.08
    _related
    0.08
    .Gradient
    0.08
    Activations Density 0.003%

    No Known Activations