© 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. 60187
    Prev
    Next
    INDEX
    Explanations

    code file extensions

    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
    igner
    -0.06
    Į
    -0.06
    دÙģ
    -0.06
     Ngo
    -0.06
    ICA
    -0.06
    woord
    -0.06
    ++]=
    -0.06
    /proto
    -0.06
    çIJĨç§ij
    -0.06
     optimized
    -0.06
    POSITIVE LOGITS
    æĻ
    0.08
    ephir
    0.08
    åĽłç´łçļĦå½±åĵį
    0.07
     jäm
    0.07
    æ¢ħæŀĹ
    0.07
    çİĭçīĮ
    0.07
    æ§ĺ
    0.07
     vole
    0.06
    ovie
    0.06
    essenger
    0.06
    Activations Density 0.250%

    No Known Activations