© 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. 22046
    Prev
    Next
    INDEX
    Explanations

    It is a fact

    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
    ustr
    -0.08
    ollen
    -0.07
    ñas
    -0.07
    ái
    -0.07
    eker
    -0.06
    -ie
    -0.06
    èģĨ
    -0.06
    PFN
    -0.06
    èĮģ
    -0.06
    Incre
    -0.06
    POSITIVE LOGITS
     пожалÑĥй
    0.08
    çī¹çļĦ
    0.08
    cia
    0.08
    åŁŁçļĦ
    0.08
    yac
    0.07
     Rajo
    0.07
    ecten
    0.07
    æľīæĥħ
    0.07
    çī¹
    0.07
    elij
    0.07
    Activations Density 0.507%

    No Known Activations