© 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. 161737
    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
    æ³¥
    -0.29
    éĻ¶
    -0.28
     fixed
    -0.27
     natural
    -0.27
    ices
    -0.27
    æĺİçĻ½
    -0.27
    ÙĪا
    -0.27
    rous
    -0.26
    ous
    -0.26
    iced
    -0.26
    POSITIVE LOGITS
    mph
    0.30
    isman
    0.29
    modifiable
    0.27
    Ĺı
    0.26
    Subset
    0.26
    ;break
    0.25
    \"";↵
    0.25
    åīĸ
    0.25
    [child
    0.25
    kap
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.