© 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. 1525
    Prev
    Next
    INDEX
    Explanations

    expression of cloned phage PhiX174 gene E

    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
    áĢŃáĢ¯áĢĦáĢº
    -0.07
    ccoli
    -0.06
     prec
    -0.06
    åĨ³
    -0.06
    λο
    -0.06
    Prec
    -0.06
     ',',
    -0.06
    cerer
    -0.05
     
    -0.05
    ÑĤим
    -0.05
    POSITIVE LOGITS
    naud
    0.09
    éĿ¢æĹł
    0.08
    reserve
    0.08
    akk
    0.07
    uest
    0.07
    osh
    0.07
    ärke
    0.07
    inkt
    0.07
    ÑīноÑģÑĤÑĮ
    0.07
    ilha
    0.07
    Activations Density 0.333%

    No Known Activations