© 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. 12321
    Prev
    Next
    INDEX
    Explanations

    more capacity, strength, or quantity

    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
    acco
    -0.07
    ROUGH
    -0.07
    åĭķæħĭ
    -0.07
    egas
    -0.07
    æīĢ幸
    -0.07
    太è¿ĩ
    -0.07
     dyn
    -0.07
    ä¿Ŀé¤Ĭ
    -0.07
    ynt
    -0.07
    dyn
    -0.07
    POSITIVE LOGITS
     despite
    0.13
     Despite
    0.11
    åį³ä½¿
    0.11
    Despite
    0.11
     trotz
    0.10
    尽管
    0.10
     inexpensive
    0.10
    åį³ä½¿åľ¨
    0.10
    åį³ä¾¿
    0.10
    åľ¨ä¸į
    0.09
    Activations Density 0.354%

    No Known Activations