© 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. 130403
    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
     percent
    -0.27
    fuck
    -0.26
     sustain
    -0.24
     Liber
    -0.23
    ï¼ħ
    -0.23
     \%
    -0.23
    åĪĨåĮĸ
    -0.23
     replen
    -0.23
    ,&
    -0.23
    dür
    -0.23
    POSITIVE LOGITS
    æŃ¦å£«
    0.30
    æ±ŁåĮĹ
    0.30
    ensible
    0.29
    æłª
    0.27
    碰
    0.26
    paced
    0.26
    quent
    0.26
    .CustomButton
    0.25
    åĶ¾
    0.24
     Frontier
    0.24
    Activations Density 9.312%

    No Known Activations

    This feature has no known activations.