© 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. 34648
    Prev
    Next
    INDEX
    Explanations

    will be

    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
    ase
    -0.07
    es
    -0.07
    /
    -0.06
    s
    -0.06
    en
    -0.06
    è¿Ļæł·çļĦæĥħåĨµ
    -0.06
    -
    -0.06
    est
    -0.06
    is
    -0.06
    ema
    -0.06
    POSITIVE LOGITS
    KeyType
    0.08
    ÑĢÑĥм
    0.08
    зей
    0.08
    roupon
    0.08
    одо
    0.08
    InputLabel
    0.08
    azier
    0.08
    ãģªãģĦãĤĪãģĨãģ«
    0.08
    resso
    0.08
    crimin
    0.08
    Activations Density 0.006%

    No Known Activations