© 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. 44173
    Prev
    Next
    INDEX
    Explanations

    information sources

    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
    §
    -0.08
    otan
    -0.07
    dit
    -0.07
    examen
    -0.07
    αιν
    -0.06
    ingi
    -0.06
    chau
    -0.06
    ÙĨا
    -0.06
    ÙĪÙĦ
    -0.06
    åħį费订éĺħ
    -0.06
    POSITIVE LOGITS
    åİĨå±Ĭ
    0.08
     confirm
    0.08
    çĶŁè¾ī
    0.08
    .getvalue
    0.07
    OrNull
    0.07
    宾
    0.07
    çĻ¾ç±³
    0.07
     atti
    0.07
    _strlen
    0.07
    _DETAILS
    0.07
    Activations Density 0.037%

    No Known Activations