© 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. 58085
    Prev
    Next
    INDEX
    Explanations

    Formatting and short words

    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
    ska
    -0.07
    £
    -0.07
    ebro
    -0.07
    say
    -0.07
    spec
    -0.07
    ogne
    -0.07
    èĢĮå½¢æĪIJ
    -0.07
    ee
    -0.07
    sä
    -0.07
    ooth
    -0.07
    POSITIVE LOGITS
    ÂŃing
    0.08
    ÂŃi
    0.07
    éĥ¨éŨèģĶåIJĪ
    0.07
    æł¹æľ¬
    0.06
    éĬĺ
    0.06
    reit
    0.06
    æĶ
    0.06
    ilah
    0.06
    ĴĪ
    0.06
    rief
    0.06
    Activations Density 0.005%

    No Known Activations