© 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. 11337
    Prev
    Next
    INDEX
    Explanations

    station data coordinates

    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
    both
    -0.09
     zowel
    -0.09
     both
    -0.09
    åIJĮæĹ¶ä¹Łè¦ģ
    -0.09
     BOTH
    -0.09
    åIJĮæŶè¿ĺè¦ģ
    -0.08
     zarówno
    -0.08
    _BOTH
    -0.08
    èĢĮä¸Ķè¿ĺæľī
    -0.08
     sowohl
    -0.08
    POSITIVE LOGITS
    obby
    0.07
    ä»ĭ
    0.07
    åħ¨åĽ½ç»Łä¸Ģ
    0.07
    åľ¨èĬ±
    0.07
    åıijå±ķä¸Ńå¿ĥ
    0.07
    IODevice
    0.07
    onen
    0.06
    scher
    0.06
    .libs
    0.06
    åĪ°å¤Ħ
    0.06
    Activations Density 0.181%

    No Known Activations