© 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. 25357
    Prev
    Next
    INDEX
    Explanations

    skin suit

    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
    orm
    -0.07
    burgh
    -0.07
    ossed
    -0.07
    chen
    -0.07
    ãĢģãĢĮ
    -0.07
    伦
    -0.07
    afil
    -0.07
    messe
    -0.07
    ç²Ł
    -0.07
    elman
    -0.06
    POSITIVE LOGITS
    æīĢæĮĩ
    0.07
    对åİŁåijĬ
    0.07
    alow
    0.07
    lau
    0.07
    loh
    0.07
    åĪ
    0.06
    åĽ¾èħ¾
    0.06
    oba
    0.06
    æĹ¥æ¸¸
    0.06
     routine
    0.06
    Activations Density 0.079%

    No Known Activations