© 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. 30280
    Prev
    Next
    INDEX
    Explanations

    circum

    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
     circum
    -0.29
     Cherry
    -0.26
     Pin
    -0.26
     Ble
    -0.25
     Circ
    -0.25
     Seas
    -0.24
    Boot
    -0.24
     Building
    -0.24
    ÑĮÑİ
    -0.24
     Cal
    -0.24
    POSITIVE LOGITS
    è´¡
    0.32
    otron
    0.27
     wing
    0.27
    /state
    0.26
    ric
    0.25
     fod
    0.25
    竦
    0.25
     Vib
    0.25
     play
    0.24
     ogs
    0.24
    Activations Density 2.071%

    No Known Activations