© 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. 32846
    Prev
    Next
    INDEX
    Explanations

    arrival and movement

    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
    ç´¯äºĨ
    -0.09
    离åİ»
    -0.09
     Shia
    -0.09
    æŁ¥çľĭæĽ´å¤ļ
    -0.09
     gam
    -0.09
    ä¸įæĸŃæī©å¤§
    -0.08
    åİŁæľīçļĦ
    -0.08
    æĶ¾å¤§
    -0.08
    è§ĴèIJ½
    -0.08
    ترا
    -0.08
    POSITIVE LOGITS
    赶æĿ¥
    0.17
    åīįæĿ¥
    0.14
    è§ģéĿ¢
    0.13
    赶赴
    0.12
    派人
    0.12
    赶åĪ°
    0.12
    éĢģæĿ¥
    0.12
    æ´¾
    0.11
     meetup
    0.11
    æĿ¥åĪ°
    0.11
    Activations Density 0.081%

    No Known Activations