© 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. 37871
    Prev
    Next
    INDEX
    Explanations

    Geometry, descriptions, theories, stable modules, planned, Copyright

    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
    éĩĩ
    -0.07
     Bio
    -0.07
     body
    -0.07
     marine
    -0.07
    ungan
    -0.06
     salt
    -0.06
     Body
    -0.06
    Bio
    -0.06
     galvan
    -0.06
     salty
    -0.06
    POSITIVE LOGITS
    ept
    0.09
    epam
    0.09
     Picasso
    0.08
    onale
    0.08
    å¾·åĪ©
    0.08
    coes
    0.08
    dak
    0.08
    .pixel
    0.08
    redit
    0.08
    они
    0.08
    Activations Density 0.023%

    No Known Activations