© 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. 50446
    Prev
    Next
    INDEX
    Explanations

    large, limit, infinity

    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
    izzly
    -0.08
    ثر
    -0.07
     bubb
    -0.07
    erset
    -0.07
    ibox
    -0.07
    acam
    -0.07
    mob
    -0.07
    eson
    -0.07
     заÑĤо
    -0.07
     Safe
    -0.07
    POSITIVE LOGITS
    uge
    0.07
    à¹ĥหà¸įà¹Ī
    0.07
    åIJµ
    0.06
    èľĴ
    0.06
    渺
    0.06
     infinite
    0.06
    éķ¿ä¹IJ
    0.06
    vore
    0.06
    çĻ¾å²ģ
    0.06
    踵
    0.06
    Activations Density 0.011%

    No Known Activations