© 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. 41618
    Prev
    Next
    INDEX
    Explanations

    Code, scientific documents

    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
     示
    -0.29
    ä¼¼
    -0.28
    ä¹ħäºĨ
    -0.28
     Sparks
    -0.27
    azo
    -0.25
    wie
    -0.25
    åĩ³
    -0.25
    _strdup
    -0.24
    Propagation
    -0.24
     IP
    -0.24
    POSITIVE LOGITS
    æłĩåĩĨ
    0.26
    âĩIJ
    0.26
    çĶŁæ´»åľ¨
    0.25
     superv
    0.24
    /core
    0.24
    ç´¢
    0.24
    orge
    0.24
    Cls
    0.24
    çĭ¬å®¶
    0.24
    rowse
    0.24
    Activations Density 0.185%

    No Known Activations