© 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. 130174
    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
    ifiable
    -0.27
     Guaranteed
    -0.26
    äºĨä¸Ģåı£
    -0.25
     kami
    -0.25
    arin
    -0.25
    oret
    -0.24
    åħ³åģľ
    -0.24
    äºĨä¸ĢäºĽ
    -0.23
     fallout
    -0.23
    iciencies
    -0.23
    POSITIVE LOGITS
    éĢı
    0.31
    transpose
    0.28
    转
    0.28
    åīĶ
    0.27
    æ¡ģ
    0.27
    antis
    0.27
    .codehaus
    0.26
     Pra
    0.26
    LOPT
    0.26
    TRAN
    0.26
    Activations Density 1.732%

    No Known Activations

    This feature has no known activations.