© 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. 30-TRANSCODER-HP
    7. 97140
    Prev
    Next
    INDEX
    Explanations

    medical/scientific texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ercul
    -0.28
     Gow
    -0.27
    çĿĢçľ¼
    -0.26
    å£ħ
    -0.26
    odule
    -0.25
    åIJĥåĪ°
    -0.24
    _drive
    -0.24
    é¢ĺ
    -0.24
    æĮĩ导
    -0.24
     Pey
    -0.24
    POSITIVE LOGITS
    unga
    0.26
    SSERT
    0.25
    imus
    0.25
    brightness
    0.25
     waivers
    0.24
    ior
    0.24
    gett
    0.24
    èĮľ
    0.23
    bh
    0.23
    ler
    0.23
    Activations Density 0.107%

    No Known Activations