© 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. 128900
    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
    reb
    -0.31
    论
    -0.28
    umper
    -0.28
    ä¸ĸ代
    -0.27
     getVersion
    -0.27
    ffb
    -0.26
     Reb
    -0.26
    çŁ³å®¶
    -0.26
    å°ģ
    -0.25
    	Version
    -0.25
    POSITIVE LOGITS
     Digest
    0.28
    å¹´è½»çļĦ
    0.26
    rium
    0.26
    é¢Ħå¤ĩ
    0.25
    tain
    0.25
    ç²īç¢İ
    0.25
     dealt
    0.24
     deal
    0.24
     *(*
    0.24
    igest
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.