© 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. 12189
    Prev
    Next
    INDEX
    Explanations

    code syntax and web addresses

    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
    çĵ
    -0.07
    alendar
    -0.06
     vice
    -0.06
    tron
    -0.06
    rix
    -0.06
    æŶåĢĻ
    -0.06
     Lone
    -0.06
    çģµå±±
    -0.05
    å®ĥ以
    -0.05
    æĹłè¨Ģ
    -0.05
    POSITIVE LOGITS
    printStats
    0.08
    paramref
    0.08
    ucch
    0.07
    eret
    0.07
    adÄĽ
    0.07
    ady
    0.07
    utique
    0.07
    zyw
    0.07
    èĺij
    0.07
    acking
    0.07
    Activations Density 0.139%

    No Known Activations