© 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. 15873
    Prev
    Next
    INDEX
    Explanations

    comparison words (similar, same, different)

    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
     sprawy
    -0.08
     Äįlánku
    -0.08
    _BINDING
    -0.07
    Ïĥκ
    -0.07
    uar
    -0.07
     vesti
    -0.07
    çĴ¨
    -0.07
     overly
    -0.07
     Année
    -0.07
    enario
    -0.07
    POSITIVE LOGITS
     overall
    0.09
     absolute
    0.08
     actual
    0.08
     total
    0.07
     respective
    0.07
     ultimate
    0.07
     subsequent
    0.07
    åħ¶
    0.07
     pula
    0.07
     value
    0.07
    Activations Density 0.227%

    No Known Activations