© 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. 142497
    Prev
    Next
    INDEX
    Explanations

    oki

    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
    ritten
    -0.27
    ifice
    -0.26
    第ä¸Ģéĥ¨
    -0.25
    ниÑĨ
    -0.25
    matic
    -0.24
    à¸Ļาà¸Ļ
    -0.24
    èĩªèIJ¥
    -0.24
    (timer
    -0.24
     оÑĩеÑĢедÑĮ
    -0.24
    log
    -0.24
    POSITIVE LOGITS
    SSION
    0.31
    èĥ½åģļåĪ°
    0.27
    éĩİ
    0.27
    yer
    0.26
    dda
    0.26
    .ser
    0.26
    å¦ĤåIJĮ
    0.25
    åIJĥåĪ°
    0.25
     fmt
    0.25
    ame
    0.25
    Activations Density 64.441%

    No Known Activations