© 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. 19-TRANSCODER-HP
    7. 9374
    Prev
    Next
    INDEX
    Explanations

    Groups

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĤ¬å´ĸ
    -0.28
    èĬľ
    -0.25
    \xaa
    -0.25
    eth
    -0.25
    æĹģ
    -0.24
    åĽłä¸ºä»ĸ们
    -0.24
    å¼ĢèĬ±
    -0.24
    纵
    -0.23
    ABL
    -0.23
     FAILURE
    -0.23
    POSITIVE LOGITS
    ni
    0.32
    ä¸Ģ对ä¸Ģ
    0.26
    Exclusive
    0.26
     ReSharper
    0.25
    vic
    0.25
    éĵĽ
    0.24
     imitation
    0.24
    nil
    0.24
    nic
    0.23
    模仿
    0.23
    Activations Density 0.021%

    No Known Activations