© 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. 23528
    Prev
    Next
    INDEX
    Explanations

    .com and punctuation

    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
    ertest
    -0.08
    antar
    -0.08
    reten
    -0.07
    ibel
    -0.07
    iqu
    -0.07
    rolet
    -0.07
    سا
    -0.07
    ChangeListener
    -0.07
    _ET
    -0.07
    oyo
    -0.07
    POSITIVE LOGITS
    tri
    0.07
    è´·
    0.06
    ç¼ĸ
    0.06
    ocha
    0.06
    åİĨ
    0.06
    ç»ŀ
    0.06
    izzo
    0.06
    ugn
    0.06
    кÑĢе
    0.06
    red
    0.06
    Activations Density 0.953%

    No Known Activations