© 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. 39563
    Prev
    Next
    INDEX
    Explanations

    web development

    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
    strap
    -0.27
    çħ§çīĩ
    -0.27
     nextState
    -0.26
    HttpRequest
    -0.25
     Stadium
    -0.25
     parked
    -0.25
    wort
    -0.24
    èĨ¨èĥĢ
    -0.23
     clicking
    -0.23
     Relatives
    -0.23
    POSITIVE LOGITS
    ä¸įæĪIJ
    0.31
    Written
    0.31
     written
    0.29
     Written
    0.28
    lo
    0.28
     incompetence
    0.28
     misses
    0.27
    ilent
    0.27
     Kou
    0.27
     incompetent
    0.26
    Activations Density 0.203%

    No Known Activations