© 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. 12-TRANSCODER-HP
    7. 24240
    Prev
    Next
    INDEX
    Explanations

    ena

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Tun
    -0.28
    èħķ
    -0.28
    æĹłçº¿çĶµ
    -0.25
    æĸ«
    -0.25
     Eph
    -0.24
    èĴī
    -0.24
     Tune
    -0.24
    isher
    -0.24
     tun
    -0.24
    åıĤä¿Ŀ
    -0.24
    POSITIVE LOGITS
     airflow
    0.32
     aire
    0.32
     circulation
    0.29
    é£İ
    0.27
    flows
    0.27
     boundaries
    0.27
    河水
    0.27
     air
    0.26
    æİĴ
    0.26
     Reynolds
    0.26
    Activations Density 0.002%

    No Known Activations