© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36201
    Prev
    Next
    INDEX
    Explanations

    eyewear and glasses

    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
    æĮŀ
    -0.09
    æį¶
    -0.09
    åľ¨åIJĮä¸Ģ
    -0.09
    èĤ¡
    -0.09
    衾
    -0.09
     Nä
    -0.08
    _LSB
    -0.08
    lse
    -0.08
    ä¹ĭå¿ĥ
    -0.08
     escal
    -0.08
    POSITIVE LOGITS
    çľ¼éķľ
    0.17
     glasses
    0.14
    佩æĪ´
    0.12
     sunglasses
    0.12
     Glasses
    0.11
    带ä¸Ĭ
    0.11
    帽åŃIJ
    0.11
    ç©¿æĪ´
    0.11
    æĪ´
    0.11
     goggles
    0.11
    Activations Density 0.098%

    No Known Activations