© 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. 62234
    Prev
    Next
    INDEX
    Explanations

    mathematical or code 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
    lixir
    -0.08
    ä¾Ľ
    -0.07
    kat
    -0.07
    cat
    -0.07
    onat
    -0.07
    kata
    -0.07
    aimer
    -0.07
    enhagen
    -0.06
    æĢĿæĥ³ä¸Ĭ
    -0.06
    é¼İåĬĽ
    -0.06
    POSITIVE LOGITS
    ddl
    0.08
    å®ľ
    0.08
    uschen
    0.07
    égal
    0.07
     Svil
    0.07
    çĥŃæºIJ
    0.07
    aggi
    0.07
    åıĤçħ§
    0.07
    æīĵçģ«
    0.07
    çĸĹ
    0.07
    Activations Density 0.019%

    No Known Activations