© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64417
    Prev
    Next
    INDEX
    Explanations

    letters picked without replacement

    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
    éĢ»
    -0.07
    æŀī
    -0.07
    нолог
    -0.07
    涧
    -0.07
    åIJİèĢħ
    -0.07
    uba
    -0.07
     ([
    -0.06
    edis
    -0.06
    è¡Ĩ
    -0.06
    Been
    -0.06
    POSITIVE LOGITS
    ãģĭãĤīãģł
    0.08
     infatti
    0.08
    θεν
    0.07
    chine
    0.07
    yste
    0.07
    raven
    0.07
    äºĨåķĬ
    0.07
    idar
    0.06
    åľ¨è¿Ļ个æŶåĢĻ
    0.06
    ئÛĮ
    0.06
    Activations Density 0.001%

    No Known Activations