© 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. 99202
    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
    rück
    -0.27
    åijµ
    -0.26
     Franken
    -0.26
    .INSTANCE
    -0.24
    大éĩı
    -0.24
    ()._
    -0.23
    è¿ĩå¤ļ
    -0.23
    ;;;;;;;;;;;;;;;;
    -0.23
    åĴĮ个人
    -0.23
    rire
    -0.23
    POSITIVE LOGITS
    -tier
    0.25
    æĭ³å¤´
    0.24
    sciously
    0.24
    çľĭæľĽ
    0.23
    æ°ij主çĶŁæ´»
    0.23
    æĹłå¿§
    0.23
    -uppercase
    0.22
    Namespace
    0.22
    æĹłæĦı
    0.22
    ä¸Ĭå¹´åIJĮæľŁ
    0.22
    Activations Density 0.015%

    No Known Activations

    This feature has no known activations.