© 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. 27205
    Prev
    Next
    INDEX
    Explanations

    list headers or 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
    ahari
    -0.07
     Spin
    -0.06
    arent
    -0.06
    wany
    -0.06
    uhr
    -0.06
    artal
    -0.06
    å¼¥
    -0.06
    åĽ
    -0.06
    åħīåįİ
    -0.06
    è¿ĶåĽŀ顶éĥ¨
    -0.06
    POSITIVE LOGITS
    æĸ¯åŁº
    0.08
    lair
    0.08
    以ä¸Ģ
    0.08
    åĪ¶å®ļ
    0.08
    iry
    0.08
    iglio
    0.08
     previs
    0.08
    ettino
    0.08
    TRS
    0.07
    åĪ¶è®¢
    0.07
    Activations Density 0.009%

    No Known Activations