© 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. 49751
    Prev
    Next
    INDEX
    Explanations

    loan requirements, seed yield, livestock movement, regulatory agency, vessel wall

    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
     Malone
    -0.07
    aub
    -0.07
    itzer
    -0.06
    asio
    -0.06
    ÑģÑĤавки
    -0.06
    auer
    -0.06
    Star
    -0.06
    æ²ĥå°Ķ
    -0.06
    alar
    -0.06
    alaus
    -0.06
    POSITIVE LOGITS
    æīĢå¤ĦçļĦ
    0.09
    欲
    0.08
    æīĢå¤Ħ
    0.07
    ebre
    0.07
    à¹Ģà¸Ńà¸ĩ
    0.07
    izen
    0.07
     already
    0.07
    .@
    0.07
    reh
    0.07
    èĩªèº«
    0.07
    Activations Density 0.175%

    No Known Activations