© 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. 9391
    Prev
    Next
    INDEX
    Explanations

    integrals and infinity

    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
    _commit
    -0.08
     Commit
    -0.07
    çĺ¾
    -0.07
    commit
    -0.07
    Commit
    -0.07
    ÑĪÑĤе
    -0.07
    ponsive
    -0.06
    åĴĮ责任
    -0.06
     commitment
    -0.06
    uffy
    -0.06
    POSITIVE LOGITS
    ording
    0.08
    redient
    0.08
    aldo
    0.07
    acun
    0.07
    pector
    0.07
    ç§ĺ书
    0.07
    æ±ĩ票
    0.07
    ukul
    0.07
    Rotation
    0.07
    .acquire
    0.07
    Activations Density 0.002%

    No Known Activations