© 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. 88689
    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
    Not in Any Lists

    No Comments

    Negative Logits
    alance
    -0.28
    inde
    -0.27
    hed
    -0.26
    য
    -0.25
    avax
    -0.24
    å°¼æĸ¯
    -0.24
    pecting
    -0.24
    icum
    -0.23
    হ
    -0.23
     Wolff
    -0.23
    POSITIVE LOGITS
     feder
    0.26
    èģĶéĤ¦
    0.26
    æ¸ħæ¾Ī
    0.24
     Feder
    0.23
    ä¸įåŃķ
    0.23
     observed
    0.23
     (()
    0.22
     launch
    0.22
    ORA
    0.21
    ém
    0.21
    Activations Density 0.009%

    No Known Activations

    This feature has no known activations.