© 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. 32123
    Prev
    Next
    INDEX
    Explanations

    flight and aviation

    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
    oen
    -0.10
    æĮŀ
    -0.10
    èł¹
    -0.10
    赶
    -0.09
    对ä¼ģä¸ļ
    -0.09
    _WR
    -0.09
    -scrollbar
    -0.09
    åħ¨çº¿
    -0.09
    声
    -0.09
    主线
    -0.08
    POSITIVE LOGITS
    é£ŀè¡Į
    0.19
    空ä¸Ń
    0.19
    é£ŀæľº
    0.16
    é«ĺ空
    0.16
    Flying
    0.15
     flight
    0.14
    é£ŀ
    0.14
    天空
    0.14
     flying
    0.13
    é£Ľ
    0.13
    Activations Density 0.157%

    No Known Activations