© 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. 38343
    Prev
    Next
    INDEX
    Explanations

    moderate

    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
    atical
    -0.09
    Ú©Ùĩ
    -0.08
    Äįk
    -0.08
    ergy
    -0.08
    setzen
    -0.08
    erei
    -0.08
    umul
    -0.08
    amarin
    -0.08
    еме
    -0.08
    аем
    -0.08
    POSITIVE LOGITS
    -sized
    0.10
    ëĤĺë§Ī
    0.10
    est
    0.09
    ly
    0.09
    iori
    0.09
     sized
    0.08
    oller
    0.08
    issimo
    0.08
    ç¨ĭ度ä¸Ĭ
    0.08
    estring
    0.08
    Activations Density 0.018%

    No Known Activations