© 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. 14261
    Prev
    Next
    INDEX
    Explanations

    empty list or empty object

    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
    ATUR
    -0.07
    icino
    -0.07
    ardon
    -0.07
    uluh
    -0.07
     ê·¸ë§Įíģ¼
    -0.06
    arau
    -0.06
    ews
    -0.06
    æĦŁåıĹä¸Ģä¸ĭ
    -0.06
    Wür
    -0.06
    æĪĸ许æľī
    -0.06
    POSITIVE LOGITS
     ``(
    0.07
    é»ĺ认çļĦ
    0.07
    вли
    0.07
    jang
    0.07
    éĸĭæĶ¾
    0.07
    ingleton
    0.07
    ÙĤاد
    0.07
    otella
    0.06
    ers
    0.06
    éĹŃä¸Ĭ
    0.06
    Activations Density 0.016%

    No Known Activations