© 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. 21029
    Prev
    Next
    INDEX
    Explanations

    code/programming contexts

    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
    BSITE
    -0.08
    /Documents
    -0.07
     DecimalFormat
    -0.07
    ÏģÏİ
    -0.07
    .jsp
    -0.07
    nyder
    -0.07
    ansa
    -0.07
    issan
    -0.07
    aran
    -0.07
    antum
    -0.07
    POSITIVE LOGITS
    ä½įçļĦ
    0.06
    ##_
    0.06
    vlak
    0.06
    ól
    0.06
    å¼Ģç«ĭ
    0.06
    dal
    0.06
    ева
    0.06
    çĶŁæķĪä¹ĭæĹ¥èµ·
    0.06
     eskort
    0.06
    çī¹æľīçļĦ
    0.06
    Activations Density 1.424%

    No Known Activations