© 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. 163084
    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
    ä»»åĬ¡
    -0.28
     ones
    -0.26
     Tes
    -0.25
    æĹłçŁ¥
    -0.25
    à¸Ĥà¸Ńà¸ļ
    -0.25
    tasks
    -0.24
    Tasks
    -0.24
    ãģĭãĤĮ
    -0.24
     Hoffman
    -0.24
     fore
    -0.24
    POSITIVE LOGITS
    çĶ¨å¾®ä¿¡
    0.29
    rok
    0.28
    æĶ¯æĮģåĬĽåº¦
    0.27
    ôm
    0.27
    imony
    0.25
    çŁ³å¤´
    0.25
    æĶ¹åĪ¶
    0.25
    åľ°ä¸ĭ
    0.25
    .ServiceModel
    0.24
    constructed
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.