© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63759
    Prev
    Next
    INDEX
    Explanations

    function derivatives and integrals

    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
    é¢ģ
    -0.07
    apul
    -0.06
    umbu
    -0.06
    çĽĶçĶ²
    -0.06
     Ferguson
    -0.06
    å¶ĭ
    -0.06
     dÆ°
    -0.06
    iri
    -0.06
    inium
    -0.06
    raft
    -0.06
    POSITIVE LOGITS
    åºŀ
    0.08
    usso
    0.08
    è¾Ī
    0.07
     Casc
    0.07
    assen
    0.07
    ä¹ĭéļĽ
    0.07
    éĤ»éĩĮ
    0.07
    agos
    0.07
     casc
    0.07
     neighbourhood
    0.07
    Activations Density 0.006%

    No Known Activations