© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46662
    Prev
    Next
    INDEX
    Explanations

    numbers and descriptions

    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
    va
    -0.08
    籤
    -0.07
    ambe
    -0.07
    ÙĪØ©
    -0.07
    éºĴ
    -0.07
    è·Įå®ķ
    -0.07
    çłģé¾Ħ
    -0.07
     ”
    -0.07
    èIJ¥éĶĢçŃĸçķ¥
    -0.07
    azi
    -0.06
    POSITIVE LOGITS
    Õ¸ÖĤÕ¶
    0.08
    esan
    0.08
     Merry
    0.07
    åħīè¾ī
    0.07
    esm
    0.07
    ении
    0.07
    Unt
    0.07
    ายà¸Ļ
    0.06
    ÐĺС
    0.06
    bon
    0.06
    Activations Density 0.044%

    No Known Activations