Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 23-TRANSCODER-HP
    4. 2870
    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
    iser
    -0.29
    izing
    -0.28
    asel
    -0.28
    ising
    -0.28
    ilda
    -0.27
    etail
    -0.24
    æīĵå¾Ĺ
    -0.24
     Penis
    -0.24
    arat
    -0.24
    审
    -0.23
    POSITIVE LOGITS
    缸è¿ij
    0.29
     CHR
    0.28
    è¿ĩ渡
    0.27
     themselves
    0.26
    åĨĪ
    0.25
    å¸ĥé²ģ
    0.25
     rec
    0.24
    åĥ®
    0.24
     incumb
    0.24
     itself
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.