© 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. 24249
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    è¿Ļç§įä¸ľè¥¿
    -0.08
    ambu
    -0.07
    OrNull
    -0.07
     riuscita
    -0.07
    _HANDLER
    -0.07
    iology
    -0.07
    olds
    -0.07
    iot
    -0.07
    è§Ī
    -0.07
     back
    -0.07
    POSITIVE LOGITS
     Gris
    0.07
    UES
    0.07
    upa
    0.07
    ä¸ĸ
    0.07
    éģµçºªå®Īæ³ķ
    0.06
    ewriter
    0.06
     profess
    0.06
    vos
    0.06
    ached
    0.06
    inc
    0.06
    Activations Density 0.000%

    No Known Activations