© 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. 12268
    Prev
    Next
    INDEX
    Explanations

    code comments and licensing

    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
    orne
    -0.07
    蹬
    -0.06
    lical
    -0.06
    nen
    -0.06
    ve
    -0.06
     inc
    -0.06
     ent
    -0.06
    ano
    -0.06
    idal
    -0.06
    dep
    -0.06
    POSITIVE LOGITS
     Caff
    0.08
    åĮ£
    0.08
    ights
    0.08
    -gallery
    0.08
    豪è¿Ī
    0.08
    ,ll
    0.08
    acle
    0.07
    EDE
    0.07
    ingung
    0.07
    ,{"
    0.07
    Activations Density 0.018%

    No Known Activations