© 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. 44193
    Prev
    Next
    INDEX
    Explanations

    currency symbols and amounts

    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
    ä¸Ģè·ĥ
    -0.07
    ÅĽ
    -0.07
    consult
    -0.06
     fair
    -0.06
    skap
    -0.06
    éros
    -0.06
     Parl
    -0.06
    omad
    -0.06
    뢰
    -0.06
    asher
    -0.06
    POSITIVE LOGITS
    _locals
    0.09
    çĻ¾åĪĨä¹ĭ
    0.08
    éĩijä¸Ŀ
    0.08
    orphic
    0.07
    (Level
    0.07
    IPC
    0.07
    adis
    0.07
     lũy
    0.07
    .ping
    0.07
     Bakal
    0.07
    Activations Density 0.001%

    No Known Activations