© 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. 107502
    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
    æĿ¾
    -0.30
    æĹ©
    -0.27
    管çIJĨéĥ¨éŨ
    -0.27
     Scott
    -0.26
    çĶŁäº§
    -0.25
    ulator
    -0.25
    rop
    -0.25
     å
    -0.25
    ç«¥
    -0.25
     hj
    -0.24
    POSITIVE LOGITS
    æ³¢çī¹
    0.29
    lds
    0.27
    Ļ¶
    0.26
     EITHER
    0.25
    stead
    0.25
    bred
    0.25
    åĽłåľ°
    0.24
    essler
    0.24
    imonial
    0.24
    obel
    0.24
    Activations Density 2.165%

    No Known Activations

    This feature has no known activations.