© 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. 22-TRANSCODER-HP
    7. 99257
    Prev
    Next
    INDEX
    Explanations

    Code and technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     spir
    -0.28
     patched
    -0.28
    plings
    -0.27
    rä
    -0.26
    (patch
    -0.25
    _FE
    -0.25
     libr
    -0.24
     finally
    -0.24
    说äºĨ
    -0.24
    åĸª
    -0.24
    POSITIVE LOGITS
    åı¯ä»¥ä»İ
    0.30
    éĢĢ
    0.28
    è¿Ļç§įæĥħåĨµ
    0.28
    è¿Ļä¸ĢçĤ¹
    0.27
    è¿Ļä¸Ģ
    0.27
    æĶ¾åľ¨
    0.27
    Hide
    0.27
    ide
    0.27
    è¿Ļ个éĹ®é¢ĺ
    0.26
    çŁ³å¤´
    0.25
    Activations Density 0.002%

    No Known Activations