© 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. 10778
    Prev
    Next
    INDEX
    Explanations

    integer parsing

    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
    shire
    -0.11
    ìĦľëĬĶ
    -0.09
    cura
    -0.09
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    ness
    -0.08
    Ø©
    -0.08
    thest
    -0.08
    sters
    -0.08
    oret
    -0.08
    eway
    -0.08
    POSITIVE LOGITS
    .parseInt
    0.11
    ized
    0.09
    ased
    0.08
    iated
    0.08
    esting
    0.08
    ised
    0.08
    isasi
    0.08
    ously
    0.08
    asing
    0.08
    ified
    0.08
    Activations Density 0.011%

    No Known Activations