© 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. 26436
    Prev
    Next
    INDEX
    Explanations

    homogeneous

    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
    ebar
    -0.08
     sens
    -0.08
     meas
    -0.07
    ä¿Ŀæ´ģ
    -0.07
    _PAGE
    -0.07
     WrocÅĤaw
    -0.07
    è´¨éĩıä¿Ŀè¯ģ
    -0.06
    measurement
    -0.06
    .Margin
    -0.06
     trailed
    -0.06
    POSITIVE LOGITS
     roots
    0.08
     homogeneous
    0.07
     frequencies
    0.07
    ämp
    0.07
     Roots
    0.07
    acar
    0.07
     Nghi
    0.07
    expo
    0.07
    人æĹł
    0.07
     Mano
    0.07
    Activations Density 0.007%

    No Known Activations