© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 130741
    Prev
    Next
    INDEX
    Explanations

    trade

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ssi
    -0.34
    ancement
    -0.28
    dojo
    -0.27
     Project
    -0.27
    ä¸ªé¡¹çĽ®
    -0.26
    pective
    -0.26
    enie
    -0.25
    aho
    -0.25
     Niet
    -0.25
    centration
    -0.25
    POSITIVE LOGITS
    çļĦæľ¬è´¨
    0.30
    oman
    0.28
    Ử
    0.26
    ADC
    0.26
    omatic
    0.26
    çĶ¨è½¦
    0.26
    away
    0.25
     prices
    0.25
     manifest
    0.24
     cov
    0.24
    Activations Density 14.818%

    No Known Activations