© 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. 41587
    Prev
    Next
    INDEX
    Explanations

    ports

    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
    htags
    -0.30
    iert
    -0.30
     Piece
    -0.26
     cÆ°á»Ŀng
    -0.26
    .Flush
    -0.26
    ibraries
    -0.26
    <Element
    -0.26
    è¿Ļéĥ¨çĶµå½±
    -0.25
    eling
    -0.25
    -piece
    -0.25
    POSITIVE LOGITS
    éĹªåħī
    0.30
     gez
    0.27
     spin
    0.27
     identity
    0.27
    çĶŁæ¶¯
    0.26
     identities
    0.26
    trib
    0.26
     postfix
    0.25
     assign
    0.25
    æĸ°ä¸Ģè½®
    0.25
    Activations Density 0.438%

    No Known Activations