© 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. 48118
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
    tır
    -0.09
    tures
    -0.08
    ehen
    -0.08
    ety
    -0.08
    tml
    -0.07
    urement
    -0.07
    èµ·è§ģ
    -0.07
    incid
    -0.07
    ssue
    -0.07
    lessly
    -0.07
    POSITIVE LOGITS
    ä¼ĹæīĢåij¨çŁ¥
    0.12
    Ùĩ
    0.12
    en
    0.11
    er
    0.11
    es
    0.11
    al
    0.10
    zinho
    0.10
    ive
    0.10
    hoot
    0.09
    ar
    0.09
    Activations Density 0.138%

    No Known Activations