© 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. 24567
    Prev
    Next
    INDEX
    Explanations

    units, duration, or quantities

    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
    ahmen
    -0.07
    chend
    -0.07
    åĬŀ
    -0.06
    리ì¦ĺ
    -0.06
     shl
    -0.06
    igator
    -0.06
    ucu
    -0.06
    hd
    -0.06
    odoro
    -0.06
    lius
    -0.06
    POSITIVE LOGITS
    çĶ¨æľĢ
    0.08
    åįķä½įåIJį称
    0.08
    çļĦåįķä½į
    0.08
    度éĩı
    0.08
    缸åħ³åįķä½į
    0.08
    åłĤåłĤ
    0.08
    åįķä½į
    0.07
     ulang
    0.07
    \Unit
    0.07
    à¸ģว
    0.07
    Activations Density 0.020%

    No Known Activations