© 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. 39415
    Prev
    Next
    INDEX
    Explanations

    technical forum posts

    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
     equations
    -0.27
     Franken
    -0.26
     se
    -0.25
    _duplicate
    -0.25
     Transfer
    -0.25
    setter
    -0.25
     Hast
    -0.24
    ho
    -0.24
     tests
    -0.24
     Prim
    -0.24
    POSITIVE LOGITS
    ablish
    0.29
    ulary
    0.28
     denen
    0.28
    ä¸ĩè¾Ĩ
    0.26
    olta
    0.26
    ä¸įåIJ«
    0.26
    .mixin
    0.26
    å¹²æű
    0.25
    oined
    0.25
    apore
    0.25
    Activations Density 0.201%

    No Known Activations