© 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. 50976
    Prev
    Next
    INDEX
    Explanations

    commas followed by 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
    .
    -0.07
    rick
    -0.06
    влÑıеÑĤÑģÑı
    -0.06
    -ish
    -0.06
    =
    -0.06
    bard
    -0.06
    "
    -0.06
    (es
    -0.06
    kamp
    -0.06
    (?)
    -0.06
    POSITIVE LOGITS
    ле
    0.08
    endien
    0.08
    ãĤĵãģ³
    0.08
    ÑĪеÑĢ
    0.08
    ÑĢÑĥÑĤ
    0.08
    onel
    0.08
    __',
    0.08
    ilik
    0.08
    imler
    0.08
    asar
    0.08
    Activations Density 0.107%

    No Known Activations