© 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. 16285
    Prev
    Next
    INDEX
    Explanations

    specific nouns and their context

    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
    éĤij
    -0.08
    uess
    -0.08
    occas
    -0.07
    ноÑģÑĤей
    -0.07
    nton
    -0.07
    /tasks
    -0.07
    çŀ°
    -0.07
     nhắn
    -0.07
    зоÑĢа
    -0.07
    ноÑģÑĤÑıм
    -0.07
    POSITIVE LOGITS
    -like
    0.12
    -esque
    0.10
    èĪ¬çļĦ
    0.09
    ergic
    0.09
    -enabled
    0.09
    å¼ıçļĦ
    0.08
    zilla
    0.08
    èĪ¬åľ°
    0.08
    etic
    0.08
    zerű
    0.07
    Activations Density 0.444%

    No Known Activations