© 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. 90179
    Prev
    Next
    INDEX
    Explanations

    DOI references

    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
    åĨµ
    -0.30
    åĢĴåľ¨
    -0.26
    åİŁæĸĩ
    -0.25
    åĢĴ
    -0.25
    ket
    -0.24
    æīįä¼ļ
    -0.24
    cba
    -0.23
    åİŁ
    -0.23
     Yue
    -0.23
    æīį
    -0.23
    POSITIVE LOGITS
    owie
    0.29
    继æī¿
    0.27
    ftime
    0.25
     successors
    0.25
    EventManager
    0.24
    çĶ·ç¥ŀ
    0.24
    rine
    0.24
    monic
    0.24
    atorial
    0.23
    Unmarshaller
    0.23
    Activations Density 1.199%

    No Known Activations