© 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. 23-TRANSCODER-HP
    7. 23478
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     verd
    -0.29
    æĺŃ
    -0.27
    å¡«
    -0.25
    phe
    -0.25
    æŃĮåĶ±
    -0.25
    еÑħ
    -0.24
    uye
    -0.24
    å½ĵåīįä½įç½®
    -0.23
    ä½³
    -0.23
    éļ¾å¿ĺ
    -0.23
    POSITIVE LOGITS
    igen
    0.28
     Buccane
    0.28
    .SE
    0.27
    åĬłçĽŁåºĹ
    0.27
    åĹ£
    0.26
    .FR
    0.25
    antis
    0.25
    AIT
    0.25
     strm
    0.25
    fic
    0.25
    Activations Density 0.100%

    No Known Activations

    This feature has no known activations.