© 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. 22-TRANSCODER-HP
    7. 129032
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æĪĺå½¹
    -0.26
    解åĨ³äºĨ
    -0.25
    é¢Ħç®Ĺ
    -0.25
    INE
    -0.24
    iry
    -0.24
     Preconditions
    -0.24
    ä¸įå¾Ĺä¸į
    -0.23
     jars
    -0.23
    èİ«
    -0.23
    åıĮæĸ¹
    -0.23
    POSITIVE LOGITS
    osc
    0.27
    è¿ĻäºĽä¸ľè¥¿
    0.27
     Shack
    0.26
    reas
    0.24
    atem
    0.23
    usu
    0.23
    atever
    0.23
    scratch
    0.23
    emas
    0.23
    _black
    0.23
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.