© 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. 32479
    Prev
    Next
    INDEX
    Explanations

    algún, alguma, certain, quelqu'un

    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
    arium
    -0.09
    rakt
    -0.08
    elai
    -0.08
    zier
    -0.08
    ayat
    -0.07
    вей
    -0.07
    óri
    -0.07
    layers
    -0.07
    ÙĥÙĬر
    -0.07
    νοÏį
    -0.07
    POSITIVE LOGITS
    æĶ¾çŁ¢
    0.11
     else
    0.10
    /all
    0.09
    æŶåĢĻ
    0.08
    æĥħåĨµä¸ĭ
    0.08
    ä¸įç»ı
    0.08
    åŀĭåı·çļĦ
    0.08
    Else
    0.08
    upon
    0.08
    place
    0.08
    Activations Density 0.003%

    No Known Activations