© 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. 26622
    Prev
    Next
    INDEX
    Explanations

    licensed and

    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
    ilere
    -0.08
    Ùıع
    -0.07
    [âĢ¦]
    -0.07
    âĢ
    -0.07
    亦åı¯
    -0.07
    -0.07
     suppl
    -0.07
    Âł
    -0.06
     stringWith
    -0.06
    Å¡ÃŃm
    -0.06
    POSITIVE LOGITS
    çĺª
    0.07
    awali
    0.07
    incontro
    0.07
    ragon
    0.07
    лин
    0.07
     Stunning
    0.06
    åij¤
    0.06
    enton
    0.06
    Painter
    0.06
    -->
    0.06
    Activations Density 0.001%

    No Known Activations