© 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. 49991
    Prev
    Next
    INDEX
    Explanations

    numbers and parentheses

    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
    /
    -0.09
    ne
    -0.07
    -
    -0.07
    atern
    -0.06
    гоÑĢ
    -0.06
    _
    -0.06
    inus
    -0.06
    à¹Ģà¸Ĭิà¸ĩ
    -0.06
    åĶ§
    -0.06
    wes
    -0.06
    POSITIVE LOGITS
    <|box_end|>
    0.11
    0.10
    aiss
    0.09
    igia
    0.09
    azard
    0.09
    egal
    0.09
    idio
    0.08
    idot
    0.08
    Õ¡Õ®
    0.08
    ãģ¨ãģĵãĤįãģ«
    0.08
    Activations Density 0.003%

    No Known Activations