© 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. 51199
    Prev
    Next
    INDEX
    Explanations

    II roman numeral usage

    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
    utf
    -0.07
    -
    -0.07
    &
    -0.06
     versus
    -0.06
    æĪ¿
    -0.06
    åľ°ä¸ĭ
    -0.06
    vs
    -0.06
    æĪijä¸į
    -0.06
    åĪĩ
    -0.06
    èĢĮä¸įæĺ¯
    -0.05
    POSITIVE LOGITS
    ãĢįãĢģãĢĮ
    0.08
    å¨ģå°Ķ
    0.08
    ignano
    0.08
    биÑĢ
    0.08
    çŃīåħ¶ä»ĸ
    0.08
    ãĢįãĢĮ
    0.08
    epass
    0.08
    ooks
    0.08
    ewire
    0.08
    ASAN
    0.08
    Activations Density 0.021%

    No Known Activations