© 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. 2723
    Prev
    Next
    INDEX
    Explanations

    awarded to, launched under, built in, exchanges cytoplasmic, legend, facility, an

    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
    bish
    -0.08
    æĺ¯åĢ¼å¾Ĺ
    -0.08
    rift
    -0.07
    ikul
    -0.07
    ICIP
    -0.07
    æĥ³å¾Ĺ
    -0.07
    ocks
    -0.07
    еме
    -0.07
    åĨįæİ¥
    -0.07
    ANNEL
    -0.07
    POSITIVE LOGITS
    åºĶäºİ
    0.07
    顾åIJįæĢĿä¹ī
    0.07
    èī³éĺ³
    0.07
    j
    0.07
    osa
    0.07
    ander
    0.06
    说çĿĢ
    0.06
    osi
    0.06
    é«ĺåĩº
    0.06
    od
    0.06
    Activations Density 1.360%

    No Known Activations