© 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. 28928
    Prev
    Next
    INDEX
    Explanations

    digits and numbers

    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
    SourceType
    -0.08
    uters
    -0.08
    usa
    -0.08
     Mush
    -0.07
    ocs
    -0.07
    ëĤ©
    -0.07
    utel
    -0.07
    ¿
    -0.07
    ignite
    -0.07
    ente
    -0.07
    POSITIVE LOGITS
    ä»ĭäºİ
    0.10
     Intermediate
    0.07
     intermediate
    0.07
     poÅĽred
    0.07
    getattr
    0.07
    mittel
    0.07
    ç½®
    0.07
    梯
    0.07
    bauer
    0.07
    dol
    0.06
    Activations Density 0.060%

    No Known Activations