© 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. 49765
    Prev
    Next
    INDEX
    Explanations

    high or sufficient

    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
     than
    -0.15
    -than
    -0.13
     Than
    -0.12
    _than
    -0.12
    than
    -0.12
    Than
    -0.11
     THAN
    -0.11
     niż
    -0.09
     kuin
    -0.08
     Ñĩем
    -0.08
    POSITIVE LOGITS
     sekali
    0.09
     enough
    0.08
    (er
    0.08
    моÑĤ
    0.08
     genug
    0.08
    er
    0.08
    æŀģäºĨ
    0.08
    eer
    0.07
    ypy
    0.07
    åĴĮ丰å¯ĮçļĦ
    0.07
    Activations Density 0.216%

    No Known Activations