© 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. 50699
    Prev
    Next
    INDEX
    Explanations

    year, month, day

    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
    寡
    -0.09
    ejm
    -0.08
    ajib
    -0.08
    ä¿¡æģ¯åıĬ
    -0.07
    ê°
    -0.07
     ÑĨело
    -0.07
    ijas
    -0.07
    egar
    -0.07
    acap
    -0.07
    FileManager
    -0.07
    POSITIVE LOGITS
    ular
    0.07
    代
    0.06
     ingr
    0.06
    æĿĥå¨ģæĢ§
    0.06
    j
    0.06
    MED
    0.06
    B
    0.06
     Rank
    0.06
    ieden
    0.06
    æİĴåIJį
    0.06
    Activations Density 0.063%

    No Known Activations