© 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. 13485
    Prev
    Next
    INDEX
    Explanations

    utility class names

    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
    aille
    -0.07
    /antlr
    -0.07
    witz
    -0.06
    容
    -0.06
    ething
    -0.06
    way
    -0.06
    æĶ¾æ°´
    -0.06
    mise
    -0.06
    æŃ¢æŃ¥
    -0.06
     Coalition
    -0.06
    POSITIVE LOGITS
     methods
    0.10
    methods
    0.09
    Methods
    0.09
    _methods
    0.09
     Methods
    0.09
    Functions
    0.09
    functions
    0.09
     functions
    0.08
     Functions
    0.08
    _FUNCTIONS
    0.08
    Activations Density 0.591%

    No Known Activations