© 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. 22023
    Prev
    Next
    INDEX
    Explanations

    Copyright notices

    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
    edly
    -0.09
    opher
    -0.08
    stelle
    -0.08
    quare
    -0.07
    ↵↵
    -0.07
    à¥įड
    -0.07
    </think>
    -0.07
    sız
    -0.07
    Tumblr
    -0.07
    ument
    -0.07
    POSITIVE LOGITS
    č↵č↵č↵
    0.10
    ###
    0.09
    ####
    0.08
    agrant
    0.08
    çļĦæŶéĹ´éĩĮ
    0.08
    nda
    0.08
     ###
    0.07
    ãģħ
    0.07
    æī©å±ķèµĦæĸĻ
    0.07
    æī¬æī¬
    0.07
    Activations Density 0.452%

    No Known Activations