© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23228
    Prev
    Next
    INDEX
    Explanations

    ontic nature. hidden variables. degrowth. forces. state. party

    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
    opak
    -0.08
    rack
    -0.08
    å¿«éĢŁèİ·åıĸ
    -0.07
    rac
    -0.07
    ä¸įèī¯
    -0.07
    à¹Ģà¸ľ
    -0.07
    apid
    -0.07
    hors
    -0.07
    ycl
    -0.07
    edef
    -0.07
    POSITIVE LOGITS
    çŀ
    0.08
     Dü
    0.07
    aland
    0.07
    olland
    0.07
    ارض
    0.07
    ¢
    0.07
    ×ķר×ķת
    0.06
    çľĭå¾Ĺè§ģ
    0.06
    è¸ıè¸ıå®ŀ
    0.06
    _dropout
    0.06
    Activations Density 0.004%

    No Known Activations