© 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. 35-TRANSCODER-HP
    7. 40729
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    lev
    -0.27
    irectory
    -0.25
    larınd
    -0.25
    fter
    -0.24
     someday
    -0.24
     everyday
    -0.24
    enticate
    -0.23
    çĶŁæ´»ä¸Ń
    -0.23
    ardless
    -0.23
    quez
    -0.23
    POSITIVE LOGITS
    (async
    0.26
     Dispose
    0.24
    åIJŀ
    0.24
     Kamp
    0.24
    -An
    0.24
     Contrib
    0.24
    å¡Ķ
    0.24
    amat
    0.23
    ãģ¤ãģį
    0.23
    عاÙĨ
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.