© 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. 63195
    Prev
    Next
    INDEX
    Explanations

    looking for, supposed to, meant to, need, want

    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
    ä¸įå°±
    -0.07
    ades
    -0.07
    RIES
    -0.07
    از
    -0.07
    -src
    -0.07
    è¡Į
    -0.06
    带æĿ¥äºĨ
    -0.06
    _basename
    -0.06
    egu
    -0.06
    apis
    -0.06
    POSITIVE LOGITS
     likely
    0.11
    è¦ģæ±ĤçļĦ
    0.08
    likely
    0.08
     probably
    0.08
     wahrscheinlich
    0.08
     expected
    0.08
     wohl
    0.08
     provavelmente
    0.07
     expects
    0.07
     ожидаеÑĤÑģÑı
    0.07
    Activations Density 0.013%

    No Known Activations