© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20985
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¦ĤæŀľæĬĬ
    -0.05
     nast
    -0.05
     hab
    -0.05
     pers
    -0.05
    æĶ¾æīĭ
    -0.05
    owns
    -0.05
    çģ«æĬĬ
    -0.05
     Diary
    -0.05
    pector
    -0.05
    umin
    -0.05
    POSITIVE LOGITS
    ¬
    0.06
     úÄį
    0.06
    pel
    0.06
    èİ«åıĬ
    0.06
    äºĨä¸ĬæĿ¥
    0.06
    nud
    0.06
    åĽºå®ļ
    0.05
    å¾Ħ
    0.05
    寻常
    0.05
     HEAD
    0.05
    Activations Density 0.004%

    No Known Activations