© 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. 64195
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æĿ¥äºĨ
    -0.31
    çķ´
    -0.29
    urope
    -0.28
    æĤ¯
    -0.27
    Size
    -0.27
    æİĩ
    -0.27
    ance
    -0.27
    çľ·
    -0.26
    ç´§æİ¥çĿĢ
    -0.25
    ëł¹
    -0.25
    POSITIVE LOGITS
    toa
    0.29
    icals
    0.28
    rys
    0.27
    oot
    0.27
    opal
    0.26
    ickey
    0.26
    éĴ¿
    0.25
     VA
    0.25
    -live
    0.25
    ób
    0.24
    Activations Density 6.199%

    No Known Activations

    This feature has no known activations.