© 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. 30251
    Prev
    Next
    INDEX
    Explanations

    came

    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
    ath
    -0.30
    T
    -0.28
    anter
    -0.26
     Bolt
    -0.25
    å¹²æ¶ī
    -0.25
    oring
    -0.25
     Regression
    -0.25
    ãĤ±ãĥĥãĥĪ
    -0.24
    åĿİ
    -0.24
     regress
    -0.24
    POSITIVE LOGITS
     ben
    0.28
    zug
    0.27
    outu
    0.25
     chạm
    0.25
    venient
    0.25
    itus
    0.25
    è¿ŀ
    0.25
    éĢļ讯åijĺ
    0.24
     Dissertation
    0.24
    abcdefghijklmnopqrstuvwxyz
    0.24
    Activations Density 0.815%

    No Known Activations