© 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. 22648
    Prev
    Next
    INDEX
    Explanations

    normality, Gaussian, limit theorems, waves

    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
    èĭ±éĽĦçļĦ
    -0.08
     dere
    -0.08
    æĶ¹åıĺèĩªå·±
    -0.08
    eses
    -0.07
    ergie
    -0.07
    _Zero
    -0.07
    UGHT
    -0.07
     strate
    -0.07
    åĪ«è®©
    -0.07
    .Icon
    -0.07
    POSITIVE LOGITS
    éļıæľº
    0.08
     assumption
    0.07
     shape
    0.07
    shape
    0.07
    èĩ³å°ij
    0.07
    ptic
    0.07
    /tab
    0.06
    ìĥĿ
    0.06
     Anonymous
    0.06
    Rnd
    0.06
    Activations Density 0.004%

    No Known Activations