© 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. 31-TRANSCODER-HP
    7. 18007
    Prev
    Next
    INDEX
    Explanations

    say "years"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åįĬå°ıæŶ
    -0.28
    第äºĮ天
    -0.26
    Minute
    -0.25
    aland
    -0.25
     aged
    -0.24
     pouco
    -0.24
    gress
    -0.24
    ä¸įä¹ħ
    -0.24
    åı¦ä¸Ģè¾¹
    -0.24
    è¶Ĭ大
    -0.24
    POSITIVE LOGITS
     several
    1.06
     many
    1.03
    å¾Īå¤ļ
    0.95
    许å¤ļ
    0.94
    many
    0.91
    èĭ¥å¹²
    0.83
     Several
    0.81
     Many
    0.81
    Many
    0.79
     MANY
    0.78
    Activations Density 60.862%

    No Known Activations