© 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. 11386
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    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
    esan
    -0.10
    pliers
    -0.09
    大é¢ĺ
    -0.09
    βε
    -0.09
    æľĢæĸ°è¯Ħ论
    -0.08
     Afinal
    -0.08
    ordes
    -0.08
    è¿ĶåĽŀ顶éĥ¨
    -0.08
    plier
    -0.08
    ieur
    -0.08
    POSITIVE LOGITS
    ↵
    0.07
     (
    0.06
     specifically
    0.06
    ...
    0.06
    uf
    0.06
    ustom
    0.05
     called
    0.05
    TC
    0.05
    č↵
    0.05
    å¼Ģ
    0.05
    Activations Density 0.810%

    No Known Activations