© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4500
    Prev
    Next
    INDEX
    Explanations

    degrees

    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
    Not in Any Lists

    No Comments

    Negative Logits
     _$
    -0.08
    omme
    -0.08
    èī²åĪĹ
    -0.08
    åijĺ
    -0.08
    abled
    -0.08
    ocks
    -0.07
    æľīåĽĽ
    -0.07
    _MAY
    -0.07
     INCIDENTAL
    -0.07
    èĽĻ
    -0.07
    POSITIVE LOGITS
    èĦĬæ¢ģ
    0.06
    两æŀģ
    0.06
    dish
    0.06
    åįĹæŀģ
    0.06
     знако
    0.06
    åĮĹæŀģ
    0.06
    .forRoot
    0.06
    à¹Ĥ
    0.06
     Dread
    0.06
    缸çĪ±
    0.06
    Activations Density 0.003%

    No Known Activations