© 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. 41873
    Prev
    Next
    INDEX
    Explanations

    benefits of

    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
    itz
    -0.08
    ature
    -0.07
    åĽŀäºĭ
    -0.07
    er
    -0.07
     اÙĦÙħعÙĨÙĬØ©
    -0.07
    ulation
    -0.07
    reja
    -0.07
    _notify
    -0.07
    èļª
    -0.07
    eger
    -0.07
    POSITIVE LOGITS
    fully
    0.10
     nhuáºŃn
    0.09
     ÃŃch
    0.09
    -seeking
    0.08
    icios
    0.08
    anee
    0.08
     immédi
    0.08
     outweigh
    0.08
    ÃŃcios
    0.08
    icial
    0.08
    Activations Density 0.033%

    No Known Activations