© 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. 23582
    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
    ingly
    -0.28
    åį°è±¡
    -0.26
    ags
    -0.26
    åħ³èģĶ交æĺĵ
    -0.25
    转åŀĭåıijå±ķ
    -0.25
    -next
    -0.25
    æĢ»ç®Ĺ
    -0.24
    prung
    -0.24
    å¤Ħå¤Ħ
    -0.24
    ily
    -0.23
    POSITIVE LOGITS
    preter
    0.29
     pumped
    0.28
    æĪijçļĦå¿ĥ
    0.27
    inear
    0.27
    仪
    0.25
     fif
    0.25
    ä¸įæĪIJ
    0.25
    herits
    0.24
    sess
    0.24
     sunset
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.