© 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. 51136
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    bergen
    -0.08
    ثر
    -0.08
    .tp
    -0.07
     tp
    -0.07
    æŶè£ħåij¨
    -0.07
     milen
    -0.07
    åħ«æĸ¹
    -0.07
    ohan
    -0.07
    strup
    -0.07
     vari
    -0.06
    POSITIVE LOGITS
     lief
    0.07
    eram
    0.07
    Flying
    0.07
    çĺ¦èĤī
    0.07
    _Type
    0.07
    Nickname
    0.07
     fortal
    0.07
    ç»ĦåIJĪ
    0.07
    Launching
    0.06
    almas
    0.06
    Activations Density 0.004%

    No Known Activations