© 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. 39281
    Prev
    Next
    INDEX
    Explanations

    code or math symbols

    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
    å®Į
    -0.07
    ä¸įæĢĿ
    -0.07
    è°ĵ
    -0.07
    _RESERVED
    -0.06
    çĶ¨å°ı
    -0.06
    otu
    -0.06
    åħ±æµİ
    -0.06
    inars
    -0.06
    etur
    -0.06
    abu
    -0.06
    POSITIVE LOGITS
    ÅĽnie
    0.08
    newline
    0.08
    akeup
    0.08
    -leading
    0.07
    æĺŃ
    0.07
    intern
    0.07
    andes
    0.07
    ikum
    0.07
    åIJĭ
    0.07
    eca
    0.07
    Activations Density 0.033%

    No Known Activations