© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161839
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ¯į
    -0.28
    ores
    -0.28
    lass
    -0.27
    defs
    -0.26
    ocks
    -0.26
     Mother
    -0.26
     extensive
    -0.26
    ooled
    -0.25
     mother
    -0.25
    Cor
    -0.24
    POSITIVE LOGITS
    <_
    0.27
     !_
    0.26
    eam
    0.26
    â»ĺ
    0.26
    )\↵
    0.25
     ((_
    0.25
    ä»·éĴ±
    0.25
     _↵
    0.25
    ffective
    0.24
    ighter
    0.24
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.