© 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. 62014
    Prev
    Next
    INDEX
    Explanations

    numbers and mathematical expressions

    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
    bÄĽ
    -0.09
    ÑĢÑĥм
    -0.08
    alti
    -0.08
    ewa
    -0.08
    sweise
    -0.08
    pera
    -0.08
    trup
    -0.08
    agl
    -0.08
    kannya
    -0.08
    éĺ¿æĭī伯
    -0.07
    POSITIVE LOGITS
    uar
    0.07
    اعة
    0.07
    arith
    0.06
    æĴ²
    0.06
    ucose
    0.06
    ^
    0.06
     Merc
    0.06
    avor
    0.06
    quist
    0.06
    oleans
    0.06
    Activations Density 0.002%

    No Known Activations