© 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. 128895
    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
    ificate
    -0.28
    AppName
    -0.25
    rage
    -0.25
    okers
    -0.23
    igr
    -0.23
    izen
    -0.23
    iscal
    -0.23
    Ъ
    -0.22
    ypi
    -0.22
    ynomials
    -0.22
    POSITIVE LOGITS
    æ·±
    0.24
     alike
    0.24
    èĥ¶
    0.23
    æľīæĽ´å¤ļçļĦ
    0.22
    aat
    0.22
    TERN
    0.22
    ä¸Ģåı£æ°Ķ
    0.21
    AlgorithmException
    0.21
    äºĮ级
    0.21
    voy
    0.21
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.