© 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. 130668
    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
    ystate
    -0.30
    å¤§åľ°
    -0.27
    ynet
    -0.27
     xsi
    -0.27
    å¡Ķ
    -0.25
    stack
    -0.25
    ining
    -0.25
     swept
    -0.25
     Abs
    -0.25
    Å¡t
    -0.24
    POSITIVE LOGITS
    ä¸į认è¯Ĩ
    0.26
    åħļé£İå»īæĶ¿
    0.26
    æĵ¢
    0.26
     judgment
    0.25
    illos
    0.25
    çŀ§
    0.24
     migrationBuilder
    0.24
    .twig
    0.24
    deo
    0.24
    lington
    0.24
    Activations Density 65.063%

    No Known Activations

    This feature has no known activations.