© 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. 110937
    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
     từng
    -0.26
    çĬ¶
    -0.25
    模
    -0.24
    èĢĮå·²
    -0.24
    è£ħ
    -0.24
    æŃ£éĿ¢
    -0.23
    å°±æľīäºĨ
    -0.23
     Space
    -0.23
    åħ¨éĥ¨
    -0.23
    空éĹ´
    -0.23
    POSITIVE LOGITS
    ystack
    0.29
    ców
    0.26
    -points
    0.24
    -ins
    0.24
    edom
    0.24
    tesy
    0.23
    åĪĨ彩
    0.23
    ingly
    0.23
     discriminator
    0.22
    /lists
    0.22
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.