© 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. 10591
    Prev
    Next
    INDEX
    Explanations

    first, second, third

    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
    igg
    -0.07
    ients
    -0.06
    afe
    -0.06
    å¿ĥæĤ¦
    -0.06
    ynam
    -0.06
    plx
    -0.06
    ajar
    -0.06
    ovid
    -0.06
    ç½
    -0.06
     ìĭ¤
    -0.06
    POSITIVE LOGITS
    åħĪçľĭ
    0.10
    第ä¸Ģç§į
    0.10
    é¦ĸåħĪæĺ¯
    0.10
    第ä¸Ģéĥ¨åĪĨ
    0.09
     firstly
    0.09
     먼ìłĢ
    0.09
     pertama
    0.08
    åīįèĢħ
    0.08
    åīįåįĬ
    0.08
    第ä¸Ģ段
    0.08
    Activations Density 0.099%

    No Known Activations