© 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. 44281
    Prev
    Next
    INDEX
    Explanations

    described as

    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
    ingg
    -0.08
    amak
    -0.08
    imah
    -0.07
    å°ijåħĪ
    -0.07
    hme
    -0.06
    owoÅĽci
    -0.06
    agher
    -0.06
    QUIRE
    -0.06
     unless
    -0.06
    _except
    -0.06
    POSITIVE LOGITS
     faithfully
    0.07
    ä¸Ķåħ·æľī
    0.07
     accurately
    0.07
     correctly
    0.07
    ä¸Ķ
    0.07
     efficacement
    0.07
    æij©
    0.07
    çĶµè§Ĩ
    0.06
    磨
    0.06
     successfully
    0.06
    Activations Density 0.457%

    No Known Activations