© 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. 50087
    Prev
    Next
    INDEX
    Explanations

    about [something]

    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
    HORT
    -0.10
    weise
    -0.09
    irth
    -0.09
    ãĤĪãģĨãģ«ãģªãģ£ãģ¦
    -0.09
    ansom
    -0.09
    enov
    -0.09
    cope
    -0.09
    esz
    -0.09
    efined
    -0.09
    enom
    -0.09
    POSITIVE LOGITS
     ÙĪعÙĨ
    0.09
    ments
    0.08
    ÑģÑı
    0.08
    ãĤĭ
    0.08
    /on
    0.08
    nya
    0.08
    ness
    0.07
    ees
    0.07
    -
    0.07
    ÃŃr
    0.07
    Activations Density 0.096%

    No Known Activations