© 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. 60870
    Prev
    Next
    INDEX
    Explanations

    date arithmetic

    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
    νά
    -0.07
    รัà¸Ķ
    -0.07
    AXB
    -0.07
    duk
    -0.07
    boden
    -0.06
    çĴĥ
    -0.06
    /null
    -0.06
    å¦ŀ
    -0.06
    å½ĵ好
    -0.06
    _w
    -0.06
    POSITIVE LOGITS
    äºĽè®¸
    0.08
    å°ij许
    0.07
    iors
    0.07
    داد
    0.06
    oped
    0.06
    omore
    0.06
    å¾ij
    0.06
    ponsored
    0.06
    究
    0.06
     considerable
    0.06
    Activations Density 0.010%

    No Known Activations