© 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. 39337
    Prev
    Next
    INDEX
    Explanations

    code or mathematical expressions

    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
    urio
    -0.10
    çIJĨå·¥åѦéĻ¢
    -0.08
    adak
    -0.08
    annis
    -0.08
    请ä¸ĭè½½
    -0.08
    ovin
    -0.08
    oom
    -0.07
    æµĦ
    -0.07
    adata
    -0.07
    ADED
    -0.07
    POSITIVE LOGITS
    缴åĪ°
    0.08
     audi
    0.07
    lify
    0.07
    kle
    0.07
    elf
    0.07
     Hearing
    0.07
    _CT
    0.06
    éro
    0.06
    elseif
    0.06
    ilag
    0.06
    Activations Density 0.004%

    No Known Activations