© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58856
    Prev
    Next
    INDEX
    Explanations

    "hello", "what", "is"

    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
    AsString
    -0.07
    jur
    -0.07
    çľĭä¸Ĭåİ»
    -0.07
    人头
    -0.06
    анÑĤа
    -0.06
    åĪ«æľī
    -0.06
    enin
    -0.06
    Fun
    -0.06
    Pocket
    -0.06
    åı£
    -0.06
    POSITIVE LOGITS
    wez
    0.08
    åħ¬åı¸æ¦ĤåĨµ
    0.08
    æīĢ以大家
    0.07
    reece
    0.07
    cia
    0.07
    è¢«ä¾ĽåºĶåķĨ
    0.07
    tual
    0.07
    ÙĥÙIJ
    0.07
     atol
    0.07
    bridge
    0.07
    Activations Density 0.002%

    No Known Activations