© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23301
    Prev
    Next
    INDEX
    Explanations

    fraction{ or $$\frac{x}{y}$$

    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¿ľæĸ¹çļĦ
    -0.07
    APER
    -0.07
    _INITIALIZER
    -0.07
    ENTI
    -0.07
    对åŃ¦ä¹ł
    -0.07
    ä¸įåIJĥ
    -0.07
    edig
    -0.07
    renom
    -0.07
    OLOR
    -0.07
    .gameserver
    -0.07
    POSITIVE LOGITS
    itary
    0.08
    Ñģол
    0.06
    quare
    0.06
    ikel
    0.06
    amat
    0.06
     Met
    0.06
    ueb
    0.06
    æ¥Ń
    0.06
     Gare
    0.06
    ible
    0.06
    Activations Density 0.010%

    No Known Activations