© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17711
    Prev
    Next
    INDEX
    Explanations

    let + pronoun/determiner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ģåIJij
    -0.07
    èĥ½ä¸º
    -0.07
    æĹłæ¯Ķ
    -0.06
     blevet
    -0.06
    èµ·æĿ¥
    -0.06
    æİ¥åĪ°
    -0.06
    è¦ģ注æĦı
    -0.06
    å¥Īä½ķ
    -0.06
    cosa
    -0.06
    ometric
    -0.06
    POSITIVE LOGITS
    èĩªæµģ
    0.13
    èĩªçĶ±éĢīæĭ©
    0.10
    èĩªçĶ±æ´»åĬ¨
    0.09
    ivre
    0.09
    ä»»çĶ±
    0.08
    åħ¶èĩªçĦ¶
    0.08
    èĩªçĶ±ãģ«
    0.08
    åĢĴä¹Ł
    0.08
    äºĭæĢģ
    0.08
    åħįè´¹åľ¨çº¿
    0.08
    Activations Density 0.064%

    No Known Activations