© 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. 39485
    Prev
    Next
    INDEX
    Explanations

    increasing

    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
    ä¸įæĸŃåľ°
    -0.30
    åĽºå®ļ
    -0.29
    éĢļ
    -0.28
    éĢIJ
    -0.28
    åĽºå®ļçļĦ
    -0.26
     progressive
    -0.26
    phony
    -0.26
    è¶ĬæĿ¥è¶Ĭå¤ļ
    -0.25
    ç¢Ľ
    -0.25
    ä¸įæĸŃå®ĮåĸĦ
    -0.24
    POSITIVE LOGITS
    ajs
    0.25
    åıĺçİ°
    0.25
    arsers
    0.25
    akes
    0.25
    ves
    0.24
    ä¸ĢåĪĨéĴ±
    0.24
    ç½ijå°ıç¼ĸ
    0.24
    oblin
    0.23
    вал
    0.23
    cepts
    0.23
    Activations Density 1.821%

    No Known Activations