© 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. 44075
    Prev
    Next
    INDEX
    Explanations

    sequences followed by punctuation or special characters

    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
    from
    -0.07
    è´¯
    -0.07
    esion
    -0.07
    наÑĤ
    -0.07
    incinn
    -0.07
    atre
    -0.07
    ansen
    -0.07
    enant
    -0.06
    lier
    -0.06
    åIJ¯
    -0.06
    POSITIVE LOGITS
     عÙĦÙĬÙĩا
    0.12
     عÙĦÙĬÙĩÙħ
    0.10
     darauf
    0.10
     drauf
    0.10
     عÙĦÙĬÙĩ
    0.10
     auf
    0.09
     trên
    0.09
     på
    0.09
     onto
    0.09
     на
    0.08
    Activations Density 0.024%

    No Known Activations