© 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. 45140
    Prev
    Next
    INDEX
    Explanations

    ticket or invoice

    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
    istrator
    -0.08
    cona
    -0.07
    resher
    -0.07
    kof
    -0.07
    zor
    -0.07
    <|box_end|>
    -0.07
    efeld
    -0.07
    è²¢
    -0.07
    timeofday
    -0.07
    Ĺ
    -0.06
    POSITIVE LOGITS
    eri
    0.10
    alba
    0.08
    reuse
    0.08
    iard
    0.08
    æīĢè½½
    0.08
    eria
    0.08
    ette
    0.07
    ç°¿
    0.07
     kebenaran
    0.07
    (pi
    0.07
    Activations Density 0.033%

    No Known Activations