© 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. 163023
    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
    .argsort
    -0.34
    为æ°ij
    -0.30
    ä¸Ģäºĭ
    -0.30
    iage
    -0.28
    èī¯
    -0.27
    "<?
    -0.26
    ä¸ºä½ł
    -0.25
    <Unit
    -0.24
    沨
    -0.24
    .norm
    -0.24
    POSITIVE LOGITS
    åģıåIJij
    0.28
     Overlay
    0.26
    ç¯ĩ
    0.26
    åĨįå¤ļ
    0.25
    oscope
    0.25
    åµĮ
    0.24
    ä¸įéĢĤåIJĪ
    0.24
    沿
    0.23
     Mara
    0.23
    leshooting
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.