© 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. 36447
    Prev
    Next
    INDEX
    Explanations

    airlines and flights

    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
    èĹı
    -0.09
    å«
    -0.09
    iets
    -0.09
    海绵
    -0.09
    åŁ
    -0.09
     Avery
    -0.09
    èķ¾
    -0.08
    velt
    -0.08
    åį´æĺ¯
    -0.08
    gee
    -0.08
    POSITIVE LOGITS
    èĪªçıŃ
    0.16
    èĪªç©ºåħ¬åı¸
    0.14
    æľºç¥¨
    0.12
    âľĪ
    0.11
    大巴
    0.11
     airlines
    0.11
     flight
    0.10
     wing
    0.10
     flights
    0.09
     Airlines
    0.09
    Activations Density 0.098%

    No Known Activations