© 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. 30227
    Prev
    Next
    INDEX
    Explanations

    effectiveness

    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
    orch
    -0.28
    weed
    -0.28
    éĤĵå°ı
    -0.27
     latter
    -0.27
    è®°å¾Ĺ
    -0.25
    æ·Ģ
    -0.25
    京津
    -0.25
    rix
    -0.25
    ĥĿ
    -0.24
    elize
    -0.24
    POSITIVE LOGITS
    大åıij
    0.31
    æĿijéķĩ
    0.26
     Coff
    0.26
     reb
    0.25
    Ãły
    0.25
     permission
    0.25
    nger
    0.24
     phấn
    0.24
    ä¸įåĪĨ
    0.24
    erce
    0.24
    Activations Density 0.932%

    No Known Activations