© 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. 19676
    Prev
    Next
    INDEX
    Explanations

    text formatting and encoding errors

    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
    bron
    -0.08
    åIJįä¹ī
    -0.06
    åĴı
    -0.06
    ä¸ĢæĽ²
    -0.06
    -bootstrap
    -0.06
    åľ¨åĨħ
    -0.06
    åijĬ
    -0.06
    NotExist
    -0.06
     hypoth
    -0.06
     checkpoints
    -0.06
    POSITIVE LOGITS
     misplaced
    0.08
     formatting
    0.08
    ä¸įæĺĵ
    0.08
    _icons
    0.07
    è§Ĩè§īä¸Ĭ
    0.07
     text
    0.07
    åįĥåŃĹ
    0.07
    mien
    0.07
    _intent
    0.07
     ASCII
    0.07
    Activations Density 0.040%

    No Known Activations