© 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. 23053
    Prev
    Next
    INDEX
    Explanations

    introduction of comparative clauses

    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
    uckle
    -0.08
    ÑģÑı
    -0.07
    ellig
    -0.07
    ór
    -0.07
    iern
    -0.07
    ahuan
    -0.07
    uffs
    -0.07
    icular
    -0.07
    ellige
    -0.07
    и
    -0.07
    POSITIVE LOGITS
    ledes
    0.12
     halnya
    0.10
    ities
    0.08
    baugh
    0.08
    lada
    0.08
    对äºİ
    0.08
     sebaliknya
    0.08
    pton
    0.08
     اÙĦØŃاÙĦ
    0.07
    åħ¶å®ĥ
    0.07
    Activations Density 0.003%

    No Known Activations