© 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. 3200
    Prev
    Next
    INDEX
    Explanations

    English word beginnings

    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
     J
    -0.06
    ch
    -0.06
    base
    -0.06
    isch
    -0.06
    c
    -0.06
    gen
    -0.06
     '
    -0.06
    is
    -0.06
    asm
    -0.06
    ilt
    -0.06
    POSITIVE LOGITS
    æķĻäºİ
    0.09
    emand
    0.08
    ajer
    0.08
    åįĵ
    0.08
    çĽĬ
    0.08
     trú
    0.08
    engo
    0.08
    schlag
    0.08
    astle
    0.08
    ledo
    0.08
    Activations Density 0.045%

    No Known Activations