© 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. 129402
    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
     combined
    -0.28
    å±ķ示äºĨ
    -0.27
    .writeValue
    -0.27
    缸æ¯Ķ
    -0.27
    ä¸ĵåįĸ
    -0.27
    弥漫
    -0.26
    grand
    -0.26
    <Entry
    -0.26
    quals
    -0.26
    _BINDING
    -0.26
    POSITIVE LOGITS
    åĪ¥
    0.26
    稳妥
    0.25
    oner
    0.25
    åģĩæĹ¥
    0.24
    —one
    0.24
     conservative
    0.24
    ®
    0.24
    -safe
    0.23
    Calcul
    0.23
    Rest
    0.23
    Activations Density 2.703%

    No Known Activations

    This feature has no known activations.