© 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. 14651
    Prev
    Next
    INDEX
    Explanations

    not found

    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
    -0.07
    жи
    -0.06
    c
    -0.06
    ick
    -0.06
    ave
    -0.06
    -
    -0.06
    ower
    -0.06
    R
    -0.06
    ensitive
    -0.06
    æīİ
    -0.06
    POSITIVE LOGITS
    [âĢ¦
    0.09
    asang
    0.08
    apiro
    0.08
    _Pin
    0.08
    :start
    0.08
    äf
    0.08
    isphere
    0.08
    äºŃäºŃ
    0.07
    ıb
    0.07
    .serializer
    0.07
    Activations Density 0.010%

    No Known Activations