© 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. 557
    Prev
    Next
    INDEX
    Explanations

    code snippets (.only, Namespace, /jquery)

    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
    èĦļæīĭ
    -0.08
    å§ĶåĨħ
    -0.08
    ½Ķ
    -0.08
    ä»»ä½ķä¿Ŀè¯ģ
    -0.07
     recru
    -0.07
    onsor
    -0.07
     ube
    -0.07
    ä¸Ńæłĩåħ¬åijĬ
    -0.07
    پرد
    -0.07
    erin
    -0.07
    POSITIVE LOGITS
    el
    0.07
    ä¸ĭåIJĮ
    0.06
    ìĽ¨ìĸ´
    0.06
    ound
    0.06
    æ¡ĪçĶ±
    0.06
     à¹Ĩ
    0.05
    ream
    0.05
    ä»Ģ
    0.05
    iless
    0.05
    åĪij
    0.05
    Activations Density 0.790%

    No Known Activations