© 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. 20711
    Prev
    Next
    INDEX
    Explanations

    suffix patterns

    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
    undas
    -0.08
    ärm
    -0.08
    одо
    -0.08
    槻
    -0.07
    åı£éķĩ
    -0.07
    oppi
    -0.07
    åħ¶ä»ĸ人çļĦ
    -0.07
    _LCD
    -0.07
    иÑģÑĤÑĢи
    -0.07
    ?>>
    -0.07
    POSITIVE LOGITS
    sic
    0.08
    ence
    0.07
    ut
    0.07
    is
    0.06
    ugu
    0.06
    gui
    0.06
    uti
    0.06
     cir
    0.06
    éĩijèĬ±
    0.06
    éĩijå±±
    0.06
    Activations Density 1.602%

    No Known Activations