© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32904
    Prev
    Next
    INDEX
    Explanations

    consumer topics and related fields

    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
    ness
    -0.08
    itude
    -0.07
    ree
    -0.06
     subsequent
    -0.06
    ówczas
    -0.06
    aksana
    -0.06
     fantastic
    -0.06
    ìŀ¥
    -0.06
    upon
    -0.06
    à¸Ħà¸Ńย
    -0.06
    POSITIVE LOGITS
    erre
    0.09
    ption
    0.09
    erber
    0.09
    adini
    0.09
    haven
    0.09
    otte
    0.08
    _DEFINED
    0.08
    ivity
    0.08
     ReSharper
    0.08
    гÑĢева
    0.08
    Activations Density 0.024%

    No Known Activations