© 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. 11501
    Prev
    Next
    INDEX
    Explanations

    Illustrator, Autodesk, meshes, trim

    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
    -0.07
    pon
    -0.07
     pong
    -0.06
    æĻ®éģį
    -0.06
    /storage
    -0.06
     Pon
    -0.06
     "
    -0.06
    éī´
    -0.06
     punct
    -0.06
    é«ĺåľ°
    -0.06
    POSITIVE LOGITS
     Autodesk
    0.10
    åı³éĶ®
    0.10
    ipse
    0.09
    _AUTO
    0.09
    >Create
    0.09
    ãĥ©ãĤ¹
    0.09
    å¿«æį·éĶ®
    0.09
    æ²ĥæĸ¯
    0.08
    è¿Ľè¡Įä¿®æĶ¹
    0.08
    ssid
    0.08
    Activations Density 0.060%

    No Known Activations