© 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. 20-TRANSCODER-HP
    7. 64827
    Prev
    Next
    INDEX
    Explanations

    Economic status/income

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çijĽ
    -0.28
     Shr
    -0.28
    æ¶ķ
    -0.27
    大家åĪĨ享
    -0.26
    ordable
    -0.26
     niá»ĩm
    -0.25
    achu
    -0.25
    urable
    -0.24
    chure
    -0.24
    ected
    -0.23
    POSITIVE LOGITS
    ooth
    0.26
    |
    0.26
    cit
    0.26
    ovich
    0.25
     imposed
    0.25
    Inform
    0.24
    फ
    0.24
    precated
    0.24
    girls
    0.23
    .Lo
    0.23
    Activations Density 10.349%

    No Known Activations