© 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. 43798
    Prev
    Next
    INDEX
    Explanations

    Suppose we

    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
    ements
    -0.08
     Hitch
    -0.07
    emento
    -0.06
    æį
    -0.06
    رب
    -0.06
    aiser
    -0.06
    å·²ä¹ħ
    -0.06
    çīĩ
    -0.06
    aviours
    -0.06
    饿äºĨ
    -0.06
    POSITIVE LOGITS
     prm
    0.07
    calar
    0.07
     urgen
    0.07
    ByUrl
    0.07
    ovel
    0.07
    认éĶĻ
    0.07
    人åķĬ
    0.07
    设为é¦ĸ页
    0.07
    说ä»ĸ
    0.07
    dispatch
    0.07
    Activations Density 0.003%

    No Known Activations