© 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. 43371
    Prev
    Next
    INDEX
    Explanations

    depends on or upon

    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
    å±ŀäºİä½łçļĦ
    -0.09
    agger
    -0.09
    ä»»ä½ķéĹ®é¢ĺ
    -0.09
    ocie
    -0.08
    ureka
    -0.08
    å±ŀäºİèĩªå·±çļĦ
    -0.08
    anford
    -0.08
    opher
    -0.08
    untime
    -0.08
    icens
    -0.08
    POSITIVE LOGITS
    åıĸåĨ³äºİ
    0.13
     depends
    0.12
    depends
    0.11
     depend
    0.11
     whether
    0.11
     depended
    0.09
     depende
    0.09
     depender
    0.08
     depending
    0.08
    ä¾Ŀèµĸäºİ
    0.08
    Activations Density 0.042%

    No Known Activations