© 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. 163041
    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
    timeofday
    -0.28
    亲
    -0.26
     airs
    -0.25
    âĩĵ
    -0.25
    親
    -0.25
    uos
    -0.25
    ControlItem
    -0.24
    mani
    -0.24
    (binding
    -0.24
     Advertisement
    -0.23
    POSITIVE LOGITS
    plug
    0.26
    ..<
    0.26
     disgu
    0.26
    幡
    0.26
    éĵ¶
    0.25
    åħ«å¤§
    0.24
     augmented
    0.24
     expecting
    0.24
    ä¸ī大
    0.24
    ilver
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.