© 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. 50790
    Prev
    Next
    INDEX
    Explanations

    Roman numeral or numeric sequences

    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
    ardia
    -0.07
    çŃĴ
    -0.07
    åľ¨åIJij
    -0.07
    z
    -0.06
    j
    -0.06
     =================================================================
    -0.06
     Manning
    -0.06
    _trap
    -0.06
    åĥļ
    -0.06
    å¸ĸ
    -0.06
    POSITIVE LOGITS
    elage
    0.08
    ól
    0.08
    igem
    0.08
    ValidationError
    0.07
    ajan
    0.07
    Fach
    0.07
    å·ŀç«ĭ
    0.07
    criptor
    0.07
    æīģ
    0.07
    ueil
    0.07
    Activations Density 0.204%

    No Known Activations