© 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. 4673
    Prev
    Next
    INDEX
    Explanations

    helper functions `esc`

    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
     (
    -0.12
    (
    -0.11
    ï¼Ī
    -0.10
     ï¼Ī
    -0.09
    ãĢĤï¼Ī
    -0.09
     ];
    -0.08
     (_.
    -0.08
     ]);
    -0.07
    (...)
    -0.07
     });
    -0.07
    POSITIVE LOGITS
    adays
    0.11
    èĩªå·±
    0.11
    ostante
    0.10
    odore
    0.10
    setUp
    0.09
    bsites
    0.09
    èĩªå·±æ²¡æľī
    0.09
    phalt
    0.09
    èĩªå·±èº«ä¸Ĭ
    0.09
    óf
    0.09
    Activations Density 0.068%

    No Known Activations