© 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. 51340
    Prev
    Next
    INDEX
    Explanations

    designed, implemented, mechanisms

    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
    åIJĦé¢ĨåŁŁ
    -0.09
    åIJĦ个é¢ĨåŁŁ
    -0.07
    eneric
    -0.07
    -generic
    -0.07
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.07
    IOC
    -0.07
    алÑĥ
    -0.07
    ulon
    -0.07
    ë²Ķ
    -0.07
     corres
    -0.07
    POSITIVE LOGITS
    å·§å¦Ļ
    0.10
     ingenious
    0.09
     implemented
    0.09
    å·§å¦ĻçļĦ
    0.09
     clever
    0.09
    å·§å¦Ļåľ°
    0.09
     mechanisms
    0.09
    æľºåĪ¶
    0.08
     designed
    0.08
    缸äºĴéħįåIJĪ
    0.08
    Activations Density 0.270%

    No Known Activations