© 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. 39682
    Prev
    Next
    INDEX
    Explanations

    Dates and days

    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
     often
    -0.27
    often
    -0.27
    åij½
    -0.26
    _STRUCTURE
    -0.26
     rak
    -0.25
    ä¸Ģç§Ĵ
    -0.25
    Often
    -0.24
    ometimes
    -0.24
    å¾Ģå¾Ģ
    -0.24
     Often
    -0.24
    POSITIVE LOGITS
    tas
    0.28
     Assignment
    0.27
    åIJ¬å®Į
    0.24
    åıĺæĢģ
    0.24
    adas
    0.24
     Stout
    0.24
    åĪ³
    0.23
    Assignment
    0.23
    udiant
    0.23
     geh
    0.23
    Activations Density 0.100%

    No Known Activations