© 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. 23758
    Prev
    Next
    INDEX
    Explanations

    theory and methodology

    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
    ä¹ĭ缮çļĦ
    -0.07
    acier
    -0.07
    èĭ¦å¿ĥ
    -0.07
    ITAL
    -0.07
    OwnProperty
    -0.07
    ائÙĩ
    -0.07
     à¦ħà¦Ń
    -0.07
    åĩĮ天
    -0.07
    çĭ¼
    -0.07
    imeo
    -0.07
    POSITIVE LOGITS
    åºĶçĶ¨äºİ
    0.16
    åºĶçĶ¨åĪ°
    0.15
     applied
    0.15
    åºĶçĶ¨åľ¨
    0.13
     applic
    0.13
    è¿IJçĶ¨åĪ°
    0.13
     aplicado
    0.13
     aplicada
    0.13
     Applied
    0.12
    è¿IJçĶ¨äºİ
    0.12
    Activations Density 0.222%

    No Known Activations