© 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. 50682
    Prev
    Next
    INDEX
    Explanations

    content streams

    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
    àºŃ
    -0.07
    ``
    -0.07
    hie
    -0.07
    \_
    -0.07
    åħ¬åı¸åıijå±ķ
    -0.07
    ãģĿãĤĮãģ§
    -0.07
    ãĤ¿ãĥ¼
    -0.06
    åĽłçĪ²
    -0.06
    utor
    -0.06
    sov
    -0.06
    POSITIVE LOGITS
    ä¹Łå°±ä¸į
    0.07
    nado
    0.07
    jdbc
    0.07
    /configuration
    0.06
    ä¸įä¼ļæĺ¯
    0.06
    atoon
    0.06
    dbc
    0.06
    ersonic
    0.06
     bufio
    0.06
    ä¸įèĥ½è¯´
    0.06
    Activations Density 0.006%

    No Known Activations