© 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. 27978
    Prev
    Next
    INDEX
    Explanations

    measurements in mm

    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
    undle
    -0.08
     mut
    -0.07
    ÎŃÏģα
    -0.07
    è
    -0.07
     mand
    -0.06
     Reference
    -0.06
    Reference
    -0.06
    æĹ©æľī
    -0.06
     prem
    -0.06
    .Reference
    -0.06
    POSITIVE LOGITS
    assar
    0.08
     Cres
    0.07
    vole
    0.07
    meden
    0.07
    otty
    0.07
    eft
    0.07
    ÃŃmp
    0.07
    ä¹ĭéŃĤ
    0.07
    elix
    0.07
    "--
    0.07
    Activations Density 0.012%

    No Known Activations