© 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. 52092
    Prev
    Next
    INDEX
    Explanations

    viruses and strains

    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
    Negative Logits
     यà¥ĭà¤Ĺ
    -0.08
    ковка
    -0.07
    osit
    -0.07
    å²Ĺä½įä¸Ĭ
    -0.07
    ç«ĭåľ¨
    -0.07
    éĿłèĩªå·±
    -0.06
    avenport
    -0.06
    -done
    -0.06
    iko
    -0.06
    ort
    -0.06
    POSITIVE LOGITS
    zip
    0.08
     fragment
    0.08
    åİĨ
    0.07
     payload
    0.07
    -enter
    0.07
    å¥Īä½ķ
    0.07
     fragments
    0.07
     strains
    0.07
    tick
    0.07
     payloads
    0.07
    Activations Density 0.188%

    No Known Activations