© 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. 46125
    Prev
    Next
    INDEX
    Explanations

    static declarations in code

    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
    åѤ
    -0.08
    è¶Ĭåıij
    -0.07
    otas
    -0.07
    ŃIJ
    -0.07
    azel
    -0.07
    MainActivity
    -0.07
    éĶ¡
    -0.07
     mati
    -0.07
    tml
    -0.06
    תר
    -0.06
    POSITIVE LOGITS
    dien
    0.07
    gena
    0.07
    릿
    0.07
    forward
    0.07
    æĮīè¦ģæ±Ĥ
    0.07
    åIJįæĢĿ
    0.07
    ØŃÙĦ
    0.07
    -common
    0.07
    oner
    0.07
    no
    0.07
    Activations Density 0.061%

    No Known Activations