© 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. 7509
    Prev
    Next
    INDEX
    Explanations

    possible options

    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
    ä¸įæ²»
    -0.08
    ajak
    -0.08
    /lg
    -0.08
    oraf
    -0.08
    cind
    -0.08
    raga
    -0.08
    allah
    -0.08
    utar
    -0.07
    èıģ
    -0.07
    çļĦ缮çļĦæĺ¯
    -0.07
    POSITIVE LOGITS
    ities
    0.08
    hood
    0.08
     endless
    0.07
     ending
    0.07
     ranging
    0.07
    çīį
    0.07
    å·²ä¹ħçļĦ
    0.07
     future
    0.07
     endings
    0.07
    çļĦé«ĺä½İ
    0.07
    Activations Density 0.028%

    No Known Activations