© 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. 64247
    Prev
    Next
    INDEX
    Explanations

    boundary behaviour

    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
     Lay
    -0.08
    éĻ¢éĩĮ
    -0.07
    cord
    -0.07
     dra
    -0.06
    ãĤ¹ãĥļãĥ¼ãĤ¹
    -0.06
     konst
    -0.06
    eran
    -0.06
    Sparse
    -0.06
    engesch
    -0.06
    xdb
    -0.06
    POSITIVE LOGITS
    çķĮçļĦ
    0.09
    åĽ´
    0.09
    çķĮ
    0.09
    -facing
    0.09
    壤
    0.08
     mouths
    0.08
    /interfaces
    0.08
    æµģè¡Ģ
    0.08
    åľ©
    0.08
    åĩºéĿ¢
    0.08
    Activations Density 0.005%

    No Known Activations