© 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. 48759
    Prev
    Next
    INDEX
    Explanations

    travel time and distance

    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
    éĺİ
    -0.09
    èĥ½åģļåĪ°
    -0.09
    æĪĹ
    -0.09
    缸åĬ©
    -0.09
    涯
    -0.09
    å¥¥åľ°åĪ©
    -0.09
    дел
    -0.08
    让ä»ĸ们
    -0.08
    æĪijçľĭ
    -0.08
    ConverterFactory
    -0.08
    POSITIVE LOGITS
    交éĢļ
    0.17
    åĩºè¡Į
    0.14
    山路
    0.14
    åīįå¾Ģ
    0.14
    åħ¬åħ±äº¤éĢļ
    0.13
    è·¯ç¨ĭ
    0.13
     transportation
    0.13
    éķ¿éĢĶ
    0.13
    å¥Ķæ³¢
    0.13
     journey
    0.12
    Activations Density 0.116%

    No Known Activations