© 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. 28926
    Prev
    Next
    INDEX
    Explanations

    code blocks and curly braces

    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
    onder
    -0.08
    ÑģÑı
    -0.07
    onsor
    -0.07
    essant
    -0.07
    ç»ı管
    -0.07
    ENTO
    -0.07
    ondas
    -0.07
    IID
    -0.07
    åįģåħ¨
    -0.07
    ameda
    -0.07
    POSITIVE LOGITS
    sWith
    0.09
    arians
    0.08
    çĥ½
    0.07
    ãģĨãģ¡
    0.07
    éģĵ
    0.07
    arbon
    0.07
    sr
    0.07
    eland
    0.07
    som
    0.07
    ÅĤa
    0.06
    Activations Density 0.038%

    No Known Activations