© 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. 41400
    Prev
    Next
    INDEX
    Explanations

    Product reviews/experiences

    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
    Not in Any Lists

    No Comments

    Negative Logits
    [node
    -0.29
    ulner
    -0.29
    严谨
    -0.28
    lichkeit
    -0.28
    emer
    -0.27
    rene
    -0.27
     [[[
    -0.25
    æłĩåĩĨ
    -0.25
    çģµæ´»æĢ§
    -0.25
     Disclaimer
    -0.24
    POSITIVE LOGITS
     bast
    0.27
    赶
    0.27
    bjerg
    0.26
     Bast
    0.26
    lements
    0.25
    æĬ¼
    0.25
    ampaign
    0.24
    é¼ĵ
    0.24
     Mut
    0.24
    .fn
    0.23
    Activations Density 0.258%

    No Known Activations