© 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. 161707
    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
    èĩ´ä½¿
    -0.25
     negatively
    -0.25
    igion
    -0.24
    对ä¸ŃåĽ½
    -0.24
    åij²
    -0.23
    vidia
    -0.23
     Lev
    -0.23
    å®Įç¾İçļĦ
    -0.23
     compliment
    -0.23
    ðĿľĭ
    -0.23
    POSITIVE LOGITS
    olds
    0.26
    åħĥ
    0.26
     ns
    0.25
    .rem
    0.25
    èĢĥ
    0.25
    é¢Ĩè¢ĸ
    0.25
    (elem
    0.25
    念
    0.24
    aurus
    0.24
     elem
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.