© 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. 32816
    Prev
    Next
    INDEX
    Explanations

    scientific notation magnitudes

    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
    ually
    -0.09
    ovsky
    -0.08
    igo
    -0.08
    enu
    -0.08
    omma
    -0.07
    quo
    -0.07
    acro
    -0.07
    lement
    -0.07
    ament
    -0.07
    alu
    -0.07
    POSITIVE LOGITS
    缸è¾ħ缸æĪIJ
    0.07
    ়
    0.07
    äºĭåįĬåĬŁåĢį
    0.07
    俱ä¹IJéĥ¨
    0.07
    itters
    0.07
    erbe
    0.07
    åĬłæĭ¿å¤§
    0.06
    æ¿
    0.06
    idora
    0.06
     rah
    0.06
    Activations Density 0.003%

    No Known Activations