© 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. 1513
    Prev
    Next
    INDEX
    Explanations

    input / inputs

    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
    ayout
    -0.07
    apul
    -0.07
    aum
    -0.07
    alone
    -0.07
    OnUiThread
    -0.07
    adro
    -0.07
    å°¼äºļ
    -0.07
     Kear
    -0.07
    erable
    -0.07
    æĢĿ
    -0.07
    POSITIVE LOGITS
     inputs
    0.13
     input
    0.12
    inputs
    0.12
    input
    0.11
    è¾ĵåħ¥
    0.11
     getInput
    0.11
    _input
    0.11
     Inputs
    0.11
    è¾ĵåħ¥çļĦ
    0.10
     Input
    0.10
    Activations Density 0.293%

    No Known Activations