© 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. 62154
    Prev
    Next
    INDEX
    Explanations

    programming language tokens

    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
    gies
    -0.09
    enses
    -0.08
    pek
    -0.08
    intes
    -0.07
     Bates
    -0.07
    hares
    -0.07
    ĭ
    -0.07
    zata
    -0.07
    hoz
    -0.07
    merce
    -0.06
    POSITIVE LOGITS
    ä¸įèĥľæĶ¶
    0.07
    åºĶå½ĵä¾Ŀçħ§
    0.07
    纪åħĥ
    0.07
     Roo
    0.07
    wali
    0.07
    uib
    0.06
    at
    0.06
    otropic
    0.06
    èµ·è§ģ
    0.06
    è½®åĪ°
    0.06
    Activations Density 0.141%

    No Known Activations