© 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. 18-TRANSCODER-HP
    7. 88353
    Prev
    Next
    INDEX
    Explanations

    Sentence fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    genes
    -0.28
     mute
    -0.26
    acula
    -0.26
     ctype
    -0.25
    åĬĽè¿ĺæĺ¯
    -0.25
    ä»ĸå·²ç»ı
    -0.25
    anged
    -0.25
     Wheel
    -0.25
    UILD
    -0.25
    ografia
    -0.24
    POSITIVE LOGITS
     ob
    0.27
    åĪ·
    0.26
    -host
    0.25
     Ob
    0.25
     Marg
    0.24
    arily
    0.24
    -led
    0.24
    /Register
    0.24
     ni
    0.24
     may
    0.24
    Activations Density 24.725%

    No Known Activations