© 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. 141404
    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
    isor
    -0.28
    梯
    -0.27
     reset
    -0.27
    åŁºæķ°
    -0.26
    abeth
    -0.25
    wort
    -0.25
    åħįè´¹
    -0.24
    æ»ļçIJĥ
    -0.24
    reset
    -0.23
    isz
    -0.23
    POSITIVE LOGITS
    è¦ģåĬłå¼º
    0.27
     heaven
    0.26
    Cd
    0.26
    éĥ½è¯´
    0.25
     Certified
    0.25
    (contract
    0.24
    dig
    0.24
    ãĤ¯ãĥ©ãĥĸ
    0.24
    HELL
    0.24
     CD
    0.23
    Activations Density 57.625%

    No Known Activations

    This feature has no known activations.