© 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. 90186
    Prev
    Next
    INDEX
    Explanations

    Complete natural language sentences

    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
    åĴĮ个人
    -0.29
    åĪ¶
    -0.27
     maximum
    -0.26
     rim
    -0.26
     reminded
    -0.26
    åİŁæĸĩåľ°åĿĢ
    -0.24
    çħ
    -0.24
    Ķ
    -0.24
    çĽ
    -0.24
    åįķä½į
    -0.24
    POSITIVE LOGITS
    åİļåİļ
    0.33
    ä»įæĺ¯
    0.28
    åħ¹
    0.27
    thic
    0.27
    _SLOT
    0.26
    зв
    0.26
    严éĩįå½±åĵį
    0.25
     hosting
    0.25
    éĶĹ
    0.24
    çĿ¡è§ī
    0.24
    Activations Density 17.175%

    No Known Activations