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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162418
    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
    ece
    -0.30
    wheel
    -0.26
     Holds
    -0.25
    çļĦä¸ĢåĪĩ
    -0.25
    æĮģ
    -0.25
    enderror
    -0.25
    loader
    -0.25
    ä»Ģä¹Īéĥ½
    -0.25
    æĬĬ她
    -0.24
     poc
    -0.24
    POSITIVE LOGITS
    RITE
    0.28
    ONENT
    0.27
    主æĮģ
    0.25
    ponent
    0.25
    weg
    0.25
    :variables
    0.24
    imon
    0.24
    CRT
    0.24
    åĮ»åѦ
    0.24
     mũ
    0.24
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.