© 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. 41922
    Prev
    Next
    INDEX
    Explanations

    type and characteristics

    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
    çļĦ身影
    -0.09
    交æµģä¸İ
    -0.08
    jÃŃ
    -0.08
    اÙĬ
    -0.07
    äºĨçļĦ
    -0.07
    çݯå¢ĥä¸İ
    -0.07
    ÑĦелÑĮ
    -0.07
    æ¯ĶåĪ©
    -0.07
    åIJĮé¾Ħ
    -0.07
    åIJĮæł·çļĦ
    -0.07
    POSITIVE LOGITS
     form
    0.07
     type
    0.07
     number
    0.07
     manner
    0.07
     wording
    0.07
     format
    0.07
    urpose
    0.07
     structure
    0.07
     name
    0.07
     size
    0.06
    Activations Density 0.310%

    No Known Activations