© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2896
    Prev
    Next
    INDEX
    Explanations

    nested JSON objects and structures

    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
    nemonic
    -0.08
    _putchar
    -0.08
    ahoo
    -0.08
    blogspot
    -0.08
    عÙĦاÙħ
    -0.07
     bá»Ŀ
    -0.07
    åħī头
    -0.07
     ìĪ
    -0.07
    Runnable
    -0.07
    asics
    -0.07
    POSITIVE LOGITS
    ç»ĵæŀĦ
    0.12
    ç»ĵæŀĦçļĦ
    0.11
    ç»ĵæŀĦåĴĮ
    0.11
    structure
    0.11
    ç»ĵæŀĦä¸İ
    0.11
     structure
    0.11
     Structure
    0.10
     JSON
    0.10
     ÑģÑĤÑĢÑĥк
    0.10
     ÑģÑĤÑĢÑĥкÑĤÑĥÑĢа
    0.10
    Activations Density 0.616%

    No Known Activations