© 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. 41788
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
     canon
    -0.28
     capitals
    -0.25
     vol
    -0.25
     capitalized
    -0.25
    vol
    -0.25
    åı¬
    -0.25
    iane
    -0.25
     capital
    -0.24
    .diff
    -0.23
    mun
    -0.23
    POSITIVE LOGITS
    çݰ象
    0.28
    RequestId
    0.28
    åģ¶å°Ķ
    0.26
    éĺ²æŃ¢
    0.25
    .Dto
    0.25
    LastError
    0.25
     phenomenon
    0.25
    éĺ´éĺ³
    0.25
    常çĶ¨çļĦ
    0.24
    historic
    0.24
    Activations Density 1.520%

    No Known Activations