© 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. 13439
    Prev
    Next
    INDEX
    Explanations

    opponents or estimates

    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
    åħ¨éķ¿
    -0.07
     ball
    -0.07
    лак
    -0.06
    æīī
    -0.06
    icul
    -0.06
     ÙĪراء
    -0.06
    verst
    -0.06
    enho
    -0.06
    udas
    -0.06
    cheid
    -0.06
    POSITIVE LOGITS
    شة
    0.07
    áºŃy
    0.07
    æľ¬çľģ
    0.07
     Ogre
    0.07
    abyte
    0.07
    ritt
    0.07
    agger
    0.07
     Donn
    0.07
    uffer
    0.07
    è¹Ĥ
    0.07
    Activations Density 0.001%

    No Known Activations