© 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. 45113
    Prev
    Next
    INDEX
    Explanations

    produced by names

    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
    teria
    -0.08
    æŃ¤æ¥¼
    -0.08
    adan
    -0.08
    vej
    -0.08
    enhagen
    -0.08
     Sarkozy
    -0.08
     ngầm
    -0.07
     numel
    -0.07
    ovie
    -0.07
    tingham
    -0.07
    POSITIVE LOGITS
    Annotations
    0.08
    æķ´çIJĨ
    0.08
     excerpt
    0.08
     excerpts
    0.08
    á
    0.07
    ç´¢å¼ķ
    0.07
    OCR
    0.07
     poetic
    0.07
     transcription
    0.07
     á
    0.07
    Activations Density 0.498%

    No Known Activations