© 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. 63615
    Prev
    Next
    INDEX
    Explanations

    then expand, then draw

    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
    éĻªä½ł
    -0.07
    _checker
    -0.07
    catch
    -0.07
    æľĹæľĹ
    -0.06
    ä½ıæīĢåľ°
    -0.06
    rou
    -0.06
    immel
    -0.06
    atok
    -0.06
    æĿ¥æī¾
    -0.06
    åİĨå±Ĭ
    -0.06
    POSITIVE LOGITS
    确认åIJİ
    0.09
    å°±åľ°
    0.08
     removeFrom
    0.08
    移éĻ¤
    0.08
    Ñĥда
    0.08
    åħĪæĬĬ
    0.08
    åıijå±ķæĸ°
    0.08
    åħĪå°Ĩ
    0.08
    å°Ĩ该
    0.08
     betroffenen
    0.07
    Activations Density 0.013%

    No Known Activations