© 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. 12918
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with plus signs

    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
    dbe
    -0.09
    ervas
    -0.09
     GLenum
    -0.08
    nger
    -0.08
    lvl
    -0.08
    òng
    -0.08
    hpp
    -0.08
    deaux
    -0.07
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.07
    datum
    -0.07
    POSITIVE LOGITS
     finally
    0.07
     enfin
    0.07
     наконеÑĨ
    0.07
     Finally
    0.06
    \n
    0.06
    ect
    0.06
    åİ
    0.06
    åıįåºĶ
    0.06
    空
    0.06
    以åıĬ
    0.06
    Activations Density 0.052%

    No Known Activations