© 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. 97177
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     finally
    -0.26
    finally
    -0.25
    çļ¿
    -0.25
     stalled
    -0.24
    iya
    -0.23
    IMER
    -0.23
     ern
    -0.23
     needs
    -0.23
    .fun
    -0.23
    æĸ°åŀĭåĨłçĬ¶
    -0.23
    POSITIVE LOGITS
    å¤ļä½Ļ
    0.26
    åı¯æĥľ
    0.25
    éĹ®ä»ĸ
    0.25
    濯
    0.25
    ä»ĸè¿ĺ
    0.24
    èµŀèµı
    0.24
    çŃĶé¢ĺ
    0.23
    æĶ¶å½ķ
    0.23
    èĥĮä¸Ĭ
    0.23
    éĢıæĺİ
    0.23
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.