© 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. 41626
    Prev
    Next
    INDEX
    Explanations

    layer

    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
    urst
    -0.29
    /pkg
    -0.28
    渴
    -0.28
    ä¸įæĺİ
    -0.28
     Emer
    -0.27
    %E
    -0.27
     bl
    -0.26
    ળ
    -0.25
     seventy
    -0.25
     emerg
    -0.25
    POSITIVE LOGITS
    为äºĨ让
    0.28
    ÆĽ
    0.27
    æŶéĹ´ä¸º
    0.27
    houses
    0.25
    _MA
    0.25
    /bind
    0.25
    ProcessEvent
    0.25
    主线
    0.25
    èĻº
    0.25
    è¾Ľ
    0.24
    Activations Density 2.932%

    No Known Activations