© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 23603
    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
    Negative Logits
    éŨå¤ĸ
    -0.26
    gage
    -0.25
    Concurrency
    -0.25
    ç²²
    -0.24
    çķ¿
    -0.24
    LOOK
    -0.24
    å®ĮæĪIJ
    -0.24
     Exact
    -0.23
    æŃĮ声
    -0.23
    entry
    -0.23
    POSITIVE LOGITS
    @"
    0.25
    ATORS
    0.24
    ella
    0.24
    Indented
    0.24
     explicitly
    0.24
    REEN
    0.23
    ioxid
    0.23
    主義
    0.23
    explicit
    0.23
    rid
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.