© 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. 129712
    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
    è¿ĻçĤ¹
    -0.26
    emony
    -0.26
    Scores
    -0.26
     it
    -0.26
    å®ĥ
    -0.25
    è¿Ļä¸ĢçĤ¹
    -0.24
    é¢ł
    -0.24
    cape
    -0.24
    è¿Ļåı¥è¯Ŀ
    -0.24
    åIJĥ
    -0.24
    POSITIVE LOGITS
    ../../../
    0.31
    udit
    0.29
    reck
    0.27
    addtogroup
    0.26
    管çIJĨå·¥ä½ľ
    0.25
     unchecked
    0.25
    kre
    0.24
    AGER
    0.24
    ãĤ·
    0.24
    ãĥĩãĤ£ãĥ³ãĤ°
    0.24
    Activations Density 0.211%

    No Known Activations

    This feature has no known activations.