© 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. 12290
    Prev
    Next
    INDEX
    Explanations

    invention relates to

    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
    iali
    -0.09
    ØŃØ©
    -0.08
    agre
    -0.08
    agus
    -0.07
    ãģĺãĤģ
    -0.07
    amiento
    -0.07
    åıªè§ģ
    -0.07
    dene
    -0.07
    мÑıн
    -0.07
    åĴĮæĸ¹æ³ķ
    -0.07
    POSITIVE LOGITS
    足äºĨ
    0.06
    аÑĤов
    0.06
    bsd
    0.06
     Pu
    0.06
    arters
    0.06
     namedtuple
    0.06
    úp
    0.06
    emor
    0.06
    interop
    0.06
    ursors
    0.06
    Activations Density 0.440%

    No Known Activations