© 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. 2242
    Prev
    Next
    INDEX
    Explanations

    value of

    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
     eslint
    -0.07
    estre
    -0.07
    æ·
    -0.07
    einander
    -0.07
    ariat
    -0.07
     xuôi
    -0.07
    rompt
    -0.07
    ras
    -0.07
    cura
    -0.07
    éĥ½èĥ½çľĭåĪ°
    -0.07
    POSITIVE LOGITS
     value
    0.08
    à¸Ħà¹Īา
    0.08
    åĢ¼
    0.08
    iability
    0.08
    /values
    0.08
    éf
    0.08
    /value
    0.08
    uess
    0.07
    ê°Ĵ
    0.07
    ä¸įèı²
    0.07
    Activations Density 0.035%

    No Known Activations