© 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. 14-TRANSCODER-HP
    7. 39634
    Prev
    Next
    INDEX
    Explanations

    honors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    heimer
    -0.29
    çļĦæł¹æľ¬
    -0.26
    Trump
    -0.26
     ^^
    -0.26
     (^
    -0.25
     suche
    -0.25
    riger
    -0.24
     ^=
    -0.24
    monary
    -0.24
    UCE
    -0.24
    POSITIVE LOGITS
    ä¸įæŃ»
    0.29
    uliar
    0.26
    beg
    0.26
    pl
    0.25
    perience
    0.25
     f
    0.25
    zik
    0.25
     werk
    0.25
     infr
    0.24
     Lydia
    0.24
    Activations Density 0.320%

    No Known Activations