© 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. 18372
    Prev
    Next
    INDEX
    Explanations

    geometric mean, exponential function, logarithm

    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
    ç¢İäºĨ
    -0.09
    ç¢İçļĦ
    -0.08
    ç¢İ
    -0.07
    slot
    -0.07
    åħ½
    -0.06
    .twitter
    -0.06
     cur
    -0.06
    æ¶Īè´¹èĢħæĿĥçĽĬ
    -0.06
    ipas
    -0.06
    =$((
    -0.06
    POSITIVE LOGITS
     exponential
    0.16
     exponentially
    0.15
    ponential
    0.12
     exponent
    0.11
     logarith
    0.10
    æĮĩæķ°
    0.10
     expon
    0.09
    åĽłåŃIJ
    0.09
     Rat
    0.09
    .exp
    0.09
    Activations Density 0.075%

    No Known Activations