© 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. 49269
    Prev
    Next
    INDEX
    Explanations

    "var"

    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
    åħĨ
    -0.08
     Gig
    -0.07
    æĶĢ
    -0.07
    verkehrs
    -0.06
    ZE
    -0.06
    VD
    -0.06
    боÑĩ
    -0.06
     imagePath
    -0.06
     imageName
    -0.06
    åıijæĺİ
    -0.06
    POSITIVE LOGITS
     Mancha
    0.07
    rops
    0.07
    Ĵáŀ
    0.07
    rigen
    0.07
    æĹłè¨Ģ
    0.07
     Haup
    0.07
    erry
    0.07
    ngr
    0.07
    ERING
    0.07
     opro
    0.07
    Activations Density 0.003%

    No Known Activations