© 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. 34542
    Prev
    Next
    INDEX
    Explanations

    melan cular

    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
    yder
    -0.09
    gewater
    -0.08
    _processing
    -0.07
    ailable
    -0.07
    è¾±
    -0.07
    mér
    -0.07
    irma
    -0.07
    anie
    -0.07
    åİŁåĪĽ
    -0.07
    主
    -0.07
    POSITIVE LOGITS
    lew
    0.07
    åĽºå®ļ
    0.07
     fixed
    0.06
    åĽºå®ļçļĦ
    0.06
    åĿij
    0.06
    fixed
    0.06
    hab
    0.06
    usy
    0.06
    urna
    0.06
    erah
    0.06
    Activations Density 0.002%

    No Known Activations