© 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. 163083
    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
    åIJĦèĩª
    -0.30
    dater
    -0.27
    angible
    -0.27
    äºĶæĺŁ
    -0.26
    dling
    -0.25
    åħ³èģĶ交æĺĵ
    -0.25
     Bowen
    -0.25
    lesai
    -0.25
    èIJ±
    -0.24
    editary
    -0.24
    POSITIVE LOGITS
    为äºĨ让
    0.28
    -NLS
    0.27
    areth
    0.26
    åĬłä¹ĭ
    0.26
    çī¹åĪ«æĺ¯åľ¨
    0.24
    æ®ĸ
    0.24
    æİ¢
    0.24
     Morg
    0.23
    ä¸ĵ注äºİ
    0.23
    JD
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.