© 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. 26965
    Prev
    Next
    INDEX
    Explanations

    competition and championships

    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
    _VARIABLE
    -0.08
    ansa
    -0.08
    EDO
    -0.07
    opan
    -0.07
    iado
    -0.07
    ĻĤ
    -0.07
    stv
    -0.07
    -variable
    -0.07
    pei
    -0.07
    æѦéĻµ
    -0.07
    POSITIVE LOGITS
    illot
    0.07
    -Compatible
    0.07
    ATUR
    0.06
    å¿
    0.06
    unch
    0.06
    .INSTANCE
    0.06
    adays
    0.06
    UNCH
    0.06
    جاز
    0.06
    und
    0.06
    Activations Density 0.002%

    No Known Activations