© 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. 141073
    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
    ;base
    -0.28
     nond
    -0.26
    icit
    -0.26
    åĩłåĪĨéĴŁ
    -0.25
    (SIG
    -0.24
    çŃĭ
    -0.24
    ç¥ľ
    -0.23
     Podesta
    -0.23
    åĮĿ
    -0.23
    l
    -0.23
    POSITIVE LOGITS
    åıĤè°ĭ
    0.28
    åİŁåĽłæĺ¯
    0.27
    frau
    0.26
    讳
    0.26
    潤
    0.25
    æ´µ
    0.25
    mui
    0.25
    obbies
    0.25
    主æĮģ
    0.24
    å©ī
    0.24
    Activations Density 70.658%

    No Known Activations

    This feature has no known activations.