© 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. 42087
    Prev
    Next
    INDEX
    Explanations

    example limitation

    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
    è±Ĭ
    -0.09
    è¡·å¿ĥ
    -0.08
    çļĦ主人
    -0.07
    _yes
    -0.07
    ç¡ķæŀľ
    -0.07
     hopefully
    -0.07
    èijĨ
    -0.07
     vú
    -0.07
    èݲ
    -0.06
    nid
    -0.06
    POSITIVE LOGITS
    缺å°ij
    0.10
     insufficient
    0.09
     incorrect
    0.09
     непÑĢавилÑĮ
    0.09
     недоÑģÑĤаÑĤ
    0.09
    缺ä¹ı
    0.08
     improperly
    0.08
     Incorrect
    0.08
     inadequate
    0.08
     ìŀĺ못
    0.08
    Activations Density 0.205%

    No Known Activations