© 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. 64131
    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
     mix
    -0.28
    esen
    -0.28
     NG
    -0.26
    astically
    -0.25
    dic
    -0.25
    æĦŁè§īåĪ°
    -0.24
    pong
    -0.24
    éĽªå±±
    -0.24
    ushman
    -0.24
    è¡Įä¸ļåıijå±ķ
    -0.23
    POSITIVE LOGITS
    éĹªçĶµ
    0.27
    @",
    0.27
     Little
    0.27
    åľ°çIJĥä¸Ĭ
    0.27
    bao
    0.25
     Minimal
    0.25
    ä¸Ģç³»åĪĹ
    0.25
    Little
    0.24
    hints
    0.24
    iele
    0.24
    Activations Density 1.145%

    No Known Activations

    This feature has no known activations.