© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 533
    Prev
    Next
    INDEX
    Explanations

    proposal or firmware documents

    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
    Negative Logits
    /
    -0.07
    /c
    -0.06
    èĭ¦
    -0.06
    /v
    -0.06
     Heard
    -0.06
    åħ®
    -0.06
    åıĬåħ¶
    -0.06
     fon
    -0.06
    vette
    -0.06
    vine
    -0.06
    POSITIVE LOGITS
    æ²¹çĽIJ
    0.09
     **—
    0.08
    èļĮ
    0.08
    æĢªçļĦ
    0.08
    åģļäºĽ
    0.08
    åĪĺ家
    0.08
    adan
    0.08
    rg
    0.08
    ë¦Ħ
    0.07
    åĭĴæĸ¯
    0.07
    Activations Density 0.005%

    No Known Activations