© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32310
    Prev
    Next
    INDEX
    Explanations

    more than just

    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
    åıĬå®īåħ¨
    -0.08
    ä¼ģä¸ļåıĬ
    -0.07
    åİŁä»¶åıĬ
    -0.07
    以åıĬåħ¶ä»ĸ
    -0.07
    è¯ĬæĸŃåıĬ
    -0.07
     secr
    -0.07
    ç³»ç»ŁåıĬ
    -0.07
    fr
    -0.07
    é¡¹çĽ®åıĬ
    -0.07
    åıĬåħ¶å®ĥ
    -0.07
    POSITIVE LOGITS
    éĤ£ä¹Īç®Ģåįķ
    0.15
     alone
    0.13
     Alone
    0.12
    èĢĮæĺ¯è¦ģ
    0.12
    èĢĮåľ¨äºİ
    0.11
     semata
    0.11
    alone
    0.11
    è¿Ļä¹Īç®Ģåįķ
    0.11
    èĢĮå·²
    0.10
    åįķ纯çļĦ
    0.10
    Activations Density 0.116%

    No Known Activations