© 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. 11252
    Prev
    Next
    INDEX
    Explanations

    DEM model context

    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
     мно
    -0.07
     professionally
    -0.07
    eel
    -0.06
    ovu
    -0.06
    _MULT
    -0.06
    çŤ
    -0.06
     множ
    -0.06
    iš
    -0.06
    ,request
    -0.06
    ele
    -0.06
    POSITIVE LOGITS
    _invoke
    0.08
    endorf
    0.08
    opic
    0.08
    zil
    0.08
    andon
    0.07
    upal
    0.07
    模
    0.07
    angible
    0.07
    ucher
    0.07
    ambots
    0.07
    Activations Density 0.008%

    No Known Activations