© 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. 60495
    Prev
    Next
    INDEX
    Explanations

    transfer of information

    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
    edul
    -0.09
     Unito
    -0.08
    entifier
    -0.08
    estad
    -0.08
    een
    -0.08
     dran
    -0.08
    vard
    -0.08
     Uniti
    -0.08
     halnya
    -0.08
    -0.08
    POSITIVE LOGITS
    rence
    0.11
    able
    0.08
    latable
    0.08
    æľīèĩ´
    0.07
    /release
    0.07
    /re
    0.07
    ability
    0.07
    rible
    0.07
    i
    0.06
    IGGER
    0.06
    Activations Density 0.029%

    No Known Activations