© 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. 13417
    Prev
    Next
    INDEX
    Explanations

    Roman numerals or numbers

    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
    ies
    -0.07
    ey
    -0.07
    -0.07
    olog
    -0.06
    Âł
    -0.06
    .detach
    -0.06
    缴æİ¥æĬĬ
    -0.06
    ange
    -0.06
    解
    -0.06
    ib
    -0.06
    POSITIVE LOGITS
     abbast
    0.08
    kao
    0.08
    åł
    0.08
    大åħ¬
    0.08
    boli
    0.08
    ÑĩаÑĤки
    0.08
    åĴ
    0.07
    ÐĴС
    0.07
     rakel
    0.07
    tores
    0.07
    Activations Density 0.097%

    No Known Activations