© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30091
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables

    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
     Nadal
    -0.07
     Woods
    -0.07
    fors
    -0.07
    äºĮæľ¬
    -0.06
    gut
    -0.06
     Cop
    -0.06
     hatch
    -0.06
    udad
    -0.06
    ocal
    -0.06
    æįŁçĽĬ
    -0.06
    POSITIVE LOGITS
    æħĮ
    0.09
    ring
    0.09
    slope
    0.08
    æĹħ
    0.08
     slope
    0.07
    tn
    0.07
    chl
    0.07
    trieb
    0.07
    flight
    0.07
    attes
    0.07
    Activations Density 0.114%

    No Known Activations