© 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. 31008
    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
    tare
    -0.07
     exac
    -0.07
    ¼
    -0.07
    enstr
    -0.07
    æľºæŀĦ
    -0.07
    chel
    -0.07
    _have
    -0.07
    ä¸įåı¯ç¼ºå°ij
    -0.07
    oura
    -0.07
    »
    -0.07
    POSITIVE LOGITS
    èĻĶ
    0.07
    ept
    0.07
    æĭ¿åĩºä¸Ģ
    0.06
    åľŃ
    0.06
    iez
    0.06
    ions
    0.06
    ion
    0.06
    ote
    0.06
    è°ħ解
    0.06
    ims
    0.06
    Activations Density 0.000%

    No Known Activations