© 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. 61009
    Prev
    Next
    INDEX
    Explanations

    blog post URLs

    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
    lena
    -0.08
    izzard
    -0.07
    mine
    -0.07
    _fixture
    -0.07
    pare
    -0.07
    rezz
    -0.07
    ány
    -0.07
    Ī
    -0.07
    ç¾½
    -0.07
    çļĵ
    -0.07
    POSITIVE LOGITS
    ấp
    0.08
    wai
    0.08
    å¿Ĺ强
    0.07
    大å®Ĺ
    0.07
     Pointer
    0.07
    sold
    0.06
    ä½Ĩæĺ¯å½ĵ
    0.06
     Payne
    0.06
    溪éķĩ
    0.06
    nesc
    0.06
    Activations Density 0.004%

    No Known Activations