© 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. 11521
    Prev
    Next
    INDEX
    Explanations

    Cancel prior, .add, .string, Step left

    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
    夥
    -0.09
    åIJİèĢħ
    -0.07
    åı¦ä¸ĢåIJį
    -0.07
    åı¦ä¸Ģä½į
    -0.07
    alse
    -0.07
    æĪijçļĦè¯Ŀ
    -0.07
    othi
    -0.07
    å¼ĺ
    -0.06
    _PI
    -0.06
    åı¦
    -0.06
    POSITIVE LOGITS
    ãģ¾ãģļ
    0.07
    defs
    0.07
    rogen
    0.07
     âĶľâĶĢâĶĢ
    0.07
    åIJĮæł·æĺ¯
    0.07
    ","","
    0.06
    èĩªçĦ¶æĺ¯
    0.06
    lig
    0.06
    LAG
    0.06
    enf
    0.06
    Activations Density 0.101%

    No Known Activations