© 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. 39444
    Prev
    Next
    INDEX
    Explanations

    domain endings

    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
    æ¸į
    -0.29
    è²Ĥ
    -0.26
    mer
    -0.26
    /{}/
    -0.25
    rig
    -0.25
     li
    -0.25
    ä¸įæĪIJ
    -0.24
    aldo
    -0.24
     Tas
    -0.24
    do
    -0.23
    POSITIVE LOGITS
     Phụ
    0.28
    onne
    0.27
     Barth
    0.26
    lash
    0.26
    intl
    0.25
    .UserInfo
    0.24
    âĬĸ
    0.24
    åºĵéĩĮ
    0.24
    inator
    0.24
    åīĮ
    0.24
    Activations Density 0.741%

    No Known Activations