© 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. 52761
    Prev
    Next
    INDEX
    Explanations

    fashion industry terms

    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
    çĨĶ
    -0.11
    .nlm
    -0.10
    çĿ¾
    -0.10
    æīĺ
    -0.10
    çŁ
    -0.10
    _slice
    -0.09
    äºĮæīĭ
    -0.09
    ÑĢиÑģÑĤ
    -0.09
     ÙĨÙĬ
    -0.09
    æĬļ
    -0.09
    POSITIVE LOGITS
     garment
    0.09
    å¸ĺ
    0.08
    æŁĵ
    0.08
     Fashion
    0.08
    åŁĤ
    0.08
    å°¾
    0.08
    Ùĩر
    0.08
     Karn
    0.08
    Opaque
    0.08
    ä¸ļåĨħ
    0.08
    Activations Density 0.109%

    No Known Activations