© 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. 32291
    Prev
    Next
    INDEX
    Explanations

    two elements adjacent

    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
    ered
    -0.08
    oria
    -0.08
    achu
    -0.08
    ERR
    -0.07
    ÑĤÑĢи
    -0.07
    vole
    -0.07
    ä¹Ŀä¹Ŀ
    -0.07
    大æĬĬ
    -0.07
    viz
    -0.07
    ubat
    -0.07
    POSITIVE LOGITS
    缸éĤ»
    0.09
    ä¹ĭéĹ´
    0.08
     adjacent
    0.08
    åħĥä¹ĭéĹ´
    0.08
    ä¹ĭéĹ´çļĦè·Ŀ离
    0.08
     neighbouring
    0.08
     neighboring
    0.08
    åIJĮåı·
    0.07
     adjacency
    0.07
    adj
    0.07
    Activations Density 0.030%

    No Known Activations