© 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. 63706
    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
     ROM
    -0.28
    åıįå¤į
    -0.27
     doPost
    -0.26
    ç»IJ
    -0.26
    å½ĵä¹ĭ
    -0.26
    她æĺ¯
    -0.25
    AMY
    -0.25
    ಥ
    -0.25
    .enterprise
    -0.25
    /jav
    -0.24
    POSITIVE LOGITS
    è¶ħåĩº
    0.27
    datas
    0.26
    lies
    0.25
    rial
    0.25
     september
    0.24
    æĸĩåĮĸèīºæľ¯
    0.23
    è¥ŀ
    0.23
    æľīåħ³
    0.23
    广
    0.23
    reas
    0.23
    Activations Density 79.610%

    No Known Activations

    This feature has no known activations.