© 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. 55114
    Prev
    Next
    INDEX
    Explanations

    travel and trips

    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
    æĻļéĹ´
    -0.09
    åįĪåIJİ
    -0.09
    ä¿Ĺ
    -0.09
    åħ¥å¸Ĥ
    -0.09
    ç¯Ĩ
    -0.09
    宸
    -0.08
    SEA
    -0.08
    é¦ĸ缸
    -0.08
    åľ¨è¿ĩæ¸¡æľŁ
    -0.08
    éĢļä¿Ĺ
    -0.08
    POSITIVE LOGITS
    åĩºå·®
    0.19
    æĹħè¡Į
    0.15
    å¾Ģè¿Ķ
    0.15
    èµ´
    0.14
    æľºç¥¨
    0.13
     travel
    0.13
    å¼Ĥåľ°
    0.13
     trips
    0.13
    ä¸Ģè¶Ł
    0.13
    .visit
    0.12
    Activations Density 0.112%

    No Known Activations