© 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. 56249
    Prev
    Next
    INDEX
    Explanations

    command line

    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
    .Iter
    -0.07
    weeney
    -0.07
    .setPrototypeOf
    -0.07
    _softmax
    -0.07
    Callback
    -0.07
     callbacks
    -0.07
    åı¯åĶ®
    -0.07
    ä¸ĭåĬŁå¤«
    -0.07
    shouldBe
    -0.07
    人æīĭ
    -0.07
    POSITIVE LOGITS
    åij½ä»¤
    0.12
     commands
    0.12
     command
    0.11
    -command
    0.10
     comando
    0.10
    æĮĩ令
    0.10
    çļĦåij½ä»¤
    0.10
     Commands
    0.10
     lá»ĩnh
    0.10
    à¸Ħำสัà¹Īà¸ĩ
    0.09
    Activations Density 0.429%

    No Known Activations