© 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. 39617
    Prev
    Next
    INDEX
    Explanations

    Technical and resource-oriented text

    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
    navigator
    -0.29
    ç²Ĺ
    -0.27
    GetValue
    -0.24
    ä¸įåIJĪ
    -0.24
     unbiased
    -0.24
    çĥŁçģ«
    -0.24
    å°Ħæīĭ
    -0.24
    çĥ¬
    -0.24
    inine
    -0.24
     nuisance
    -0.24
    POSITIVE LOGITS
     herself
    0.30
     dred
    0.27
    æĬĬ她
    0.27
    à¸ķà¸Ļà¹Ģà¸Ńà¸ĩ
    0.26
    ieg
    0.26
    ç´«å¤ĸ
    0.25
     build
    0.25
    åħ¬å¼Ģåıij
    0.24
    :self
    0.24
     SELF
    0.24
    Activations Density 0.106%

    No Known Activations