© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17662
    Prev
    Next
    INDEX
    Explanations

    initiating actions like open, create, link

    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
    kowa
    -0.07
    ruz
    -0.07
    ectl
    -0.07
    åı¦æľī
    -0.07
    ssql
    -0.07
    owitz
    -0.07
     [-]:
    -0.07
     ÎŃγι
    -0.07
    ayani
    -0.07
    /topics
    -0.06
    POSITIVE LOGITS
     appropriately
    0.08
    egan
    0.07
     appropriate
    0.07
    å¿ħè¦ģçļĦ
    0.07
    fs
    0.07
     Setup
    0.07
    ена
    0.07
    ç«ĭæ¡Ī
    0.07
    æĬ¥åIJįåħ¥åı£
    0.07
    è½½
    0.07
    Activations Density 0.018%

    No Known Activations