© 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. 46355
    Prev
    Next
    INDEX
    Explanations

    override

    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
    chetti
    -0.08
    irão
    -0.08
    erken
    -0.08
    èµ·æĿ¥äºĨ
    -0.08
    eren
    -0.08
    er
    -0.08
    ième
    -0.08
    agog
    -0.08
    EGIN
    -0.08
    rad
    -0.08
    POSITIVE LOGITS
    ance
    0.07
    essus
    0.07
    باط
    0.06
    alanya
    0.06
    affer
    0.06
     Alles
    0.06
    emann
    0.06
    zbek
    0.06
    æĢ§åľ°
    0.06
    etés
    0.06
    Activations Density 0.026%

    No Known Activations