© 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. 9-TRANSCODER-HP
    7. 30366
    Prev
    Next
    INDEX
    Explanations

    ex

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    -live
    -0.26
     embr
    -0.25
    _nullable
    -0.24
    iece
    -0.24
     stem
    -0.24
    éĽ¢ãĤĮ
    -0.24
     Stem
    -0.24
    åıĹ
    -0.24
     LPC
    -0.23
    äº²çľ¼
    -0.23
    POSITIVE LOGITS
    æīĭå¥Ĺ
    0.32
    å¿ħä¸įåı¯
    0.28
    ModelError
    0.27
    iring
    0.26
    usb
    0.26
     geli
    0.26
    antes
    0.25
    ä¸ĢåĪĢ
    0.24
    AEA
    0.24
    .SOCK
    0.24
    Activations Density 5.526%

    No Known Activations