© 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. 30859
    Prev
    Next
    INDEX
    Explanations

    suitcase and luggage

    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´¥
    -0.10
    建çŃijä¸ļ
    -0.09
    éĢīåĿĢ
    -0.09
    éªı
    -0.09
     Buildings
    -0.09
    phem
    -0.09
    å¼¯æĽ²
    -0.09
    毡
    -0.09
     Kling
    -0.09
    èį¡
    -0.09
    POSITIVE LOGITS
    è¡ĮæĿİ
    0.16
     luggage
    0.15
    æīĺè¿IJ
    0.15
     baggage
    0.13
     suitcase
    0.11
    æĶ¶æĭ¾
    0.11
    æĹħéĢĶ
    0.11
    æIJºå¸¦
    0.10
    è¿ĩåħ³
    0.10
    é»ijèī²
    0.10
    Activations Density 0.052%

    No Known Activations