© 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. 41417
    Prev
    Next
    INDEX
    Explanations

    orange

    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
    ->[
    -0.26
    _exc
    -0.25
    .SP
    -0.25
    iaÅĤa
    -0.25
    ç½Ķ
    -0.25
    å°ij女
    -0.24
    æ½®æµģ
    -0.24
    {id
    -0.24
     Pirates
    -0.24
    åħ´å¥ĭ
    -0.23
    POSITIVE LOGITS
    é£ĺ
    0.29
    æĺ¯ä¸Ģ项
    0.27
    oub
    0.26
    rect
    0.26
    isi
    0.25
    uta
    0.25
    chen
    0.25
     heat
    0.25
    åĢ¾åIJ¬
    0.24
     listeners
    0.24
    Activations Density 0.333%

    No Known Activations