© 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. 55390
    Prev
    Next
    INDEX
    Explanations

    social polymers

    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
    <-
    -0.07
    oux
    -0.07
    ¦
    -0.06
    ع
    -0.06
    æĹłæĿĥ
    -0.06
     vic
    -0.06
    åı¯ä½¿çĶ¨
    -0.06
    åı¯ä¸į
    -0.06
     stitch
    -0.06
    lle
    -0.06
    POSITIVE LOGITS
    bsp
    0.08
    angkan
    0.08
    reeze
    0.08
    æĸ¯é¡¿
    0.08
    icÃŃ
    0.08
    _coverage
    0.08
    enner
    0.07
    icidad
    0.07
    erro
    0.07
    unden
    0.07
    Activations Density 0.014%

    No Known Activations