© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 140554
    Prev
    Next
    INDEX
    Explanations

    Filler words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     pony
    -0.27
    åĢĻ
    -0.27
    коÑģ
    -0.26
    OMET
    -0.24
    emed
    -0.24
     (#
    -0.24
    .Fore
    -0.24
    ('(
    -0.23
    表çݰ为
    -0.23
    .esp
    -0.23
    POSITIVE LOGITS
    çİ°åľ¨å¾Īå¤ļ
    0.34
    æĪijä»¬åľ¨
    0.28
     bot
    0.28
    ä»ĬæĻļ
    0.26
    ä»Ĭ天
    0.26
    èĭ¦
    0.26
    åĵī
    0.25
    çļĦéĩįè¦ģæĢ§
    0.25
    å¹³æŶ
    0.25
     tonight
    0.25
    Activations Density 90.736%

    No Known Activations