© 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. 39361
    Prev
    Next
    INDEX
    Explanations

    describing qualities and materials

    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
    ase
    -0.08
    and
    -0.08
    UCH
    -0.07
    ะ
    -0.07
    chnik
    -0.06
    je
    -0.06
    uch
    -0.06
    ://
    -0.06
    quals
    -0.06
    ä¸Ģ个ç®ĢåįķçļĦ
    -0.06
    POSITIVE LOGITS
    ãģĤãĤĭãģĦãģ¯
    0.08
    μη
    0.08
    ç«Ļç«Ļ
    0.08
    ãĤĤãģĹãģıãģ¯
    0.08
    ä¸Ģç«Ļ
    0.08
    以åѦçĶŁ
    0.08
     non
    0.08
     voire
    0.08
    νοÏį
    0.08
    主æĮģä¼ļè®®
    0.08
    Activations Density 0.076%

    No Known Activations