© 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. 51075
    Prev
    Next
    INDEX
    Explanations

    explores e-book

    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
    衬
    -0.06
    _FL
    -0.06
     (~(
    -0.06
    åĨ²å¤©
    -0.06
    FACE
    -0.06
    ĵ¨
    -0.06
    ception
    -0.06
    åĶ¾
    -0.06
    ÙĪاج
    -0.06
    оÑī
    -0.06
    POSITIVE LOGITS
    -hide
    0.07
    åĩĢæ°´
    0.07
    _BIND
    0.07
    æľ¬åľº
    0.07
    onta
    0.07
    éļİ
    0.07
     advisory
    0.06
    _some
    0.06
    ased
    0.06
    åĸĤ
    0.06
    Activations Density 0.001%

    No Known Activations