© 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. 19377
    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
    çķ¥
    -0.07
    aven
    -0.07
    avers
    -0.07
    /umd
    -0.07
    anye
    -0.07
    Ùģار
    -0.06
    åĵį
    -0.06
    inalg
    -0.06
    igar
    -0.06
     شعر
    -0.06
    POSITIVE LOGITS
     Vieira
    0.07
    æı´
    0.07
    BOUND
    0.07
    bat
    0.07
    rend
    0.07
    rim
    0.07
    Ïĥμ
    0.07
    ׳×Ļת
    0.07
    ç¬ĥ
    0.07
    è¡
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.