© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 38174
    Prev
    Next
    INDEX
    Explanations

    cable and jumper

    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
    è¡Įæķ°
    -0.06
    ä½įæķ°
    -0.06
    /rfc
    -0.06
    _FORE
    -0.06
    èĵ
    -0.06
    æ¯ĵ
    -0.06
     
    -0.05
     Conserv
    -0.05
     anhand
    -0.05
    ieur
    -0.05
    POSITIVE LOGITS
     connecting
    0.09
    mlin
    0.09
    çļĦè¿ŀæİ¥
    0.09
    éĢļå¾Ģ
    0.09
    è¿ŀæİ¥
    0.09
    connecting
    0.08
    åıĮåIJij
    0.08
     connections
    0.08
    bid
    0.08
     Äijứt
    0.08
    Activations Density 0.008%

    No Known Activations