© 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. 163091
    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
    _CID
    -0.28
    è·¨
    -0.28
    è¿ĻäºĽéĹ®é¢ĺ
    -0.26
    ä½İå»ī
    -0.26
    immel
    -0.25
    KH
    -0.24
    clid
    -0.24
    indow
    -0.24
    æľĪèĸª
    -0.24
    ersen
    -0.23
    POSITIVE LOGITS
    æĴ¬
    0.28
    çĪĨæĸĻ
    0.25
     robert
    0.25
    PORT
    0.25
    æIJŀ好
    0.24
    ãģŁãĤĬ
    0.24
     Colbert
    0.24
    çģ°å°ĺ
    0.24
    à¸ķà¸Ļ
    0.23
    æŶæĬ¥
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.