© 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. 162841
    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
    quirer
    -0.29
    è§ĴèIJ½
    -0.27
    éĢļçŁ¥ä¹¦
    -0.26
    ä¸Ģ头
    -0.25
    å·±
    -0.25
     cheesy
    -0.24
     corners
    -0.24
    çijģ
    -0.24
     licens
    -0.24
    éĻ²
    -0.23
    POSITIVE LOGITS
     Collins
    0.28
    ,col
    0.25
    .wik
    0.24
    inges
    0.24
    iment
    0.24
    .COL
    0.24
    COL
    0.24
     Eff
    0.24
     teleport
    0.24
    éĩįå¤į
    0.23
    Activations Density 0.012%

    No Known Activations

    This feature has no known activations.