© 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. 3005
    Prev
    Next
    INDEX
    Explanations

    names and records

    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
    åįİ缼
    -0.07
    <|box_end|>
    -0.07
    acqu
    -0.06
    大红
    -0.06
    åħļæĢ§ä¿®åħ»
    -0.06
    天éķ¿
    -0.06
    åºķä¸ĭ
    -0.06
    вок
    -0.06
    ÙģÙĤ
    -0.06
    dar
    -0.06
    POSITIVE LOGITS
     OTHERWISE
    0.08
    izr
    0.07
    edImage
    0.07
    ectiv
    0.07
    pragma
    0.07
    AGMA
    0.07
    ovel
    0.07
    .splitext
    0.07
    "class
    0.07
    Otherwise
    0.07
    Activations Density 0.073%

    No Known Activations