© 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. 129703
    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
     increased
    -0.26
    ote
    -0.25
    orough
    -0.25
    è¸Ŀ
    -0.25
    ParameterValue
    -0.24
     sed
    -0.24
     MediaType
    -0.24
     Increased
    -0.23
     Sed
    -0.23
    ont
    -0.23
    POSITIVE LOGITS
    éģ®
    0.28
    好人
    0.27
    ISTER
    0.27
    åı¯ä»¥èİ·å¾Ĺ
    0.27
    表
    0.26
    frag
    0.26
    ä¸įä»ħèĥ½
    0.25
    ACY
    0.25
    -question
    0.24
    滿
    0.24
    Activations Density 3.173%

    No Known Activations

    This feature has no known activations.