© 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. 18445
    Prev
    Next
    INDEX
    Explanations

    question 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
     Postar
    -0.07
    åħ¹
    -0.07
    yer
    -0.06
    _literals
    -0.06
    StartTime
    -0.06
    Locator
    -0.06
    agini
    -0.06
    LECT
    -0.06
    gene
    -0.06
    agul
    -0.06
    POSITIVE LOGITS
    trak
    0.10
    ä¸įå¼Ģ
    0.08
    ÙħاÙĦ
    0.07
    è®®
    0.07
    ACES
    0.07
     ensuite
    0.07
    rompt
    0.07
    PTY
    0.07
    ;/*
    0.07
    à¸Ńม
    0.06
    Activations Density 0.026%

    No Known Activations