© 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. 64468
    Prev
    Next
    INDEX
    Explanations

    Chinese and Korean characters

    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
    rowse
    -0.08
    åħ¶çľŁå®ŀæĢ§
    -0.08
    ắn
    -0.08
    æħ¢æħ¢åľ°
    -0.08
    .jquery
    -0.07
    asso
    -0.07
    .sec
    -0.07
    Lgs
    -0.07
    å¾·åįİ
    -0.07
    pgsql
    -0.07
    POSITIVE LOGITS
    åij½
    0.08
    åĢ¾åIJij
    0.08
    认å®ļçļĦ
    0.07
     ê°ķì¡°
    0.07
     Clement
    0.07
    åĪĻ认为
    0.07
    å°ĨæĮīçħ§
    0.07
    åij½é¢ĺ
    0.07
    ieb
    0.07
    强è°ĥ
    0.07
    Activations Density 0.004%

    No Known Activations