© 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. 4748
    Prev
    Next
    INDEX
    Explanations

    javascript object methods

    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
    edException
    -0.09
    er
    -0.09
    /or
    -0.08
    erb
    -0.08
    ever
    -0.08
    ÑıÑĢ
    -0.08
    erlo
    -0.08
    æĪĸå¤ļ个
    -0.08
    ×Ļ×Ļ×Ŀ
    -0.07
    attoo
    -0.07
    POSITIVE LOGITS
    ìį¨
    0.13
    errer
    0.11
    Ùij
    0.10
    ê¹IJ
    0.10
    irn
    0.09
    ere
    0.09
    .eclipse
    0.08
    erring
    0.08
    rect
    0.08
    ord
    0.08
    Activations Density 0.751%

    No Known Activations