© 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. 46299
    Prev
    Next
    INDEX
    Explanations

    examples in action or clinical contexts

    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
    oret
    -0.07
    ä¸ĢåĪĩ
    -0.07
     Teacher
    -0.07
    ain
    -0.06
    ç¢İ
    -0.06
     Avis
    -0.06
    çĿĢä¸ĢèĤ¡
    -0.06
    ostas
    -0.06
     Pred
    -0.06
    vait
    -0.06
    POSITIVE LOGITS
    ä¸įèĥľ
    0.09
    åħ·ä½ĵçļĦ
    0.09
     scenarios
    0.09
    ä¾ĭåŃIJ
    0.09
    æĪIJåĬŁæ¡Īä¾ĭ
    0.08
    ä¸ĵ项治çIJĨ
    0.08
    æ¡Īä¾ĭ
    0.08
     ìĤ¬ë¡Ģ
    0.08
    udah
    0.08
    å®ŀäºĭ
    0.08
    Activations Density 0.044%

    No Known Activations