© 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. 55736
    Prev
    Next
    INDEX
    Explanations

    z-axis or caregivers

    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
    »
    -0.08
    ále
    -0.07
    åī¯ä¼ļéķ¿
    -0.07
    íĥģ
    -0.07
    å½°
    -0.07
     hoại
    -0.07
    ages
    -0.07
    bij
    -0.07
    åĨ¤
    -0.07
    (({
    -0.07
    POSITIVE LOGITS
    ombine
    0.07
    gear
    0.06
    ÙĤدس
    0.06
    辯
    0.06
    quarters
    0.06
    oros
    0.06
    endeur
    0.06
    eron
    0.06
     dioxide
    0.06
    .alt
    0.06
    Activations Density 0.008%

    No Known Activations