© 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. 30236
    Prev
    Next
    INDEX
    Explanations

    equations with single letters

    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
     neither
    -0.07
    ়
    -0.07
    -
    -0.06
    éĿŀ
    -0.06
    —
    -0.06
    ä¹ĭ大
    -0.06
    ç¯ĩä¸Ģ
    -0.06
    o
    -0.06
    ä¾Ŀæŧ
    -0.06
    ä¸Ĭå°ıåѦ
    -0.06
    POSITIVE LOGITS
    æĪĸå°ij
    0.10
    adays
    0.10
    tlement
    0.09
    <|box_end|>
    0.08
    urch
    0.08
    erior
    0.08
    èĩªå·±
    0.08
    antal
    0.08
    awang
    0.08
    Sharper
    0.08
    Activations Density 0.068%

    No Known Activations