© 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. 63980
    Prev
    Next
    INDEX
    Explanations

    parenthetical content

    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
    s
    -0.23
    o
    -0.21
    es
    -0.17
    a
    -0.17
    Ùĩ
    -0.16
    د
    -0.16
    ت
    -0.15
    d
    -0.15
    an
    -0.15
    ات
    -0.15
    POSITIVE LOGITS
    lectual
    0.13
    odore
    0.13
    <|box_end|>
    0.12
    terior
    0.12
    jenigen
    0.12
    utenant
    0.11
    ndx
    0.11
    翼翼
    0.11
    tempts
    0.11
    annya
    0.11
    Activations Density 0.197%

    No Known Activations