© 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. 24774
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
    iven
    -0.07
    ìĸ´ëĤĺ
    -0.07
    ory
    -0.07
    Ùģض
    -0.06
     alongside
    -0.06
    angelo
    -0.06
    coli
    -0.06
    hg
    -0.06
    aza
    -0.06
    ery
    -0.06
    POSITIVE LOGITS
    istol
    0.08
     unpl
    0.07
    çī©
    0.07
    ÃģT
    0.07
    ática
    0.07
    ãĤ³ãĥ¢
    0.06
    amá
    0.06
    áticos
    0.06
     Caz
    0.06
     sout
    0.06
    Activations Density 0.028%

    No Known Activations