© 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. 23920
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols in code or math

    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
    ymb
    -0.08
     dri
    -0.07
     Branco
    -0.06
    ÙĤÙĬÙĨ
    -0.06
     ehren
    -0.06
    çŃīåIJĮäºİ
    -0.06
    缸æ¯Ķäºİ
    -0.06
    esch
    -0.06
    wo
    -0.06
    _CRYPTO
    -0.06
    POSITIVE LOGITS
    走好
    0.08
    reserve
    0.08
    empor
    0.08
    Vir
    0.08
     Vir
    0.08
    agni
    0.08
    anka
    0.08
    anking
    0.08
    ptest
    0.07
    inkin
    0.07
    Activations Density 0.006%

    No Known Activations