© 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. 31795
    Prev
    Next
    INDEX
    Explanations

    numerical separators or titles

    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
     ê°ĻìĿĢ
    -0.06
    icens
    -0.06
    类似
    -0.06
    åįķä¸ĢçļĦ
    -0.06
    åħĪåľ¨
    -0.06
    åĥıæĪij
    -0.06
     similarly
    -0.06
    çĻ½å¸¦
    -0.06
     initially
    -0.06
    petto
    -0.06
    POSITIVE LOGITS
    cord
    0.08
    çİ¥
    0.08
    ï½ľ
    0.08
    dej
    0.08
    åħ¶äºº
    0.07
    æĿ¥åķ¦
    0.07
    <![
    0.07
    feat
    0.07
    _-_
    0.07
    çī¹æĸ°
    0.07
    Activations Density 1.081%

    No Known Activations