© 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. 39505
    Prev
    Next
    INDEX
    Explanations

    measurement units

    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
    ت
    -0.08
    als
    -0.07
    os
    -0.07
    ÑģÑĮ
    -0.07
    er
    -0.07
    اتÙĩ
    -0.07
    e
    -0.06
    ات
    -0.06
    sa
    -0.06
    ral
    -0.06
    POSITIVE LOGITS
    <|box_end|>
    0.10
    å°Ķåħĭ
    0.09
    çī¹æĸ¯
    0.08
    áĢ²áĢ·
    0.08
    ä¹İ
    0.08
    .gov
    0.08
    _initializer
    0.08
    ühren
    0.08
    Vien
    0.08
    sthrough
    0.08
    Activations Density 0.020%

    No Known Activations