© 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. 32265
    Prev
    Next
    INDEX
    Explanations

    structural components in technical descriptions

    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
    rana
    -0.06
    inste
    -0.06
    éĻIJåĪ¶æĢ§
    -0.06
    è°ĥçłĶåijĺ
    -0.06
    çłĶ究ä¸İ
    -0.06
    åħ¶èĩªçĦ¶
    -0.06
    жда
    -0.05
    Einst
    -0.05
    ä¹ĥ
    -0.05
    reator
    -0.05
    POSITIVE LOGITS
    AtA
    0.07
    请ä¸İæĪij们èģĶç³»
    0.07
    ummer
    0.07
    aval
    0.07
    .bn
    0.07
    awal
    0.07
     bernama
    0.07
     (::
    0.07
    è¾īæĺł
    0.07
    ìĭľíĶ¼
    0.07
    Activations Density 0.204%

    No Known Activations