© 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. 1160
    Prev
    Next
    INDEX
    Explanations

    input/output structure

    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
    ney
    -0.08
    éľĩ
    -0.07
    .ly
    -0.07
    neys
    -0.07
    ×ķש
    -0.07
    vind
    -0.07
     Fo
    -0.06
    gni
    -0.06
    æ¯ķä¸ļçĶŁçļĦ
    -0.06
    _RUNTIME
    -0.06
    POSITIVE LOGITS
     inputs
    0.10
    inputs
    0.10
     input
    0.09
    è¾ĵåħ¥çļĦ
    0.09
    è¾ĵåħ¥
    0.08
     Inputs
    0.08
    Inputs
    0.08
     Input
    0.08
    ä¸Ńè¾ĵåħ¥
    0.08
    input
    0.08
    Activations Density 0.001%

    No Known Activations