© 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. 37628
    Prev
    Next
    INDEX
    Explanations

    .js file identifiers

    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
    _modules
    -0.07
    &P
    -0.07
    _mock
    -0.06
     vigore
    -0.06
    éªĭ
    -0.06
    åĨį说äºĨ
    -0.06
    æĩ
    -0.06
    Mock
    -0.06
    moz
    -0.06
    æĪı
    -0.06
    POSITIVE LOGITS
    çݯçIJĥ
    0.07
    审åĪ¤åijĺ
    0.07
    paired
    0.07
    abr
    0.06
    å°ijè§ģ
    0.06
    enic
    0.06
    enia
    0.06
    apa
    0.06
    .nlm
    0.06
    è¿ĺæĺ¯ä¸į
    0.06
    Activations Density 0.229%

    No Known Activations