© 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. 21467
    Prev
    Next
    INDEX
    Explanations

    export statements and return values

    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
    iran
    -0.08
    óf
    -0.08
    datagrid
    -0.07
    orex
    -0.07
    lipse
    -0.07
    jaman
    -0.07
    å¿ħçŃĶ
    -0.07
    ebben
    -0.07
    egos
    -0.07
    å¾·åĪ©
    -0.07
    POSITIVE LOGITS
    å¼łå°ı
    0.07
    åIJĦæī§
    0.07
     prés
    0.07
    -access
    0.07
    APH
    0.06
    Native
    0.06
    æĹ
    0.06
     Native
    0.06
    native
    0.06
     forEach
    0.06
    Activations Density 0.087%

    No Known Activations