© 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. 28245
    Prev
    Next
    INDEX
    Explanations

    code index positions

    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
    梦
    -0.07
    ä¸ĢæıIJ
    -0.07
    éĤ£å¹´
    -0.07
    ãĥķãĥŃ
    -0.07
    èĢģäºĨ
    -0.07
    rei
    -0.07
    寿åij½
    -0.06
    åĴĨ
    -0.06
    èĬľ
    -0.06
    iant
    -0.06
    POSITIVE LOGITS
     Plen
    0.07
    _git
    0.07
    esser
    0.07
    -bot
    0.06
    atr
    0.06
    _utils
    0.06
    è°ģæĺ¯
    0.06
    atria
    0.06
     bottleneck
    0.06
    .processor
    0.06
    Activations Density 0.004%

    No Known Activations