© 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. 90094
    Prev
    Next
    INDEX
    Explanations

    percentages

    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
    åıijåĩº
    -0.33
    ingen
    -0.29
    ë°ľ
    -0.26
    è¡Ķ
    -0.26
    主æĦı
    -0.26
     Ingen
    -0.25
    äºĨä»ĸçļĦ
    -0.25
    åıijå¸ĥä¼ļ
    -0.25
     Charg
    -0.24
    åıij
    -0.24
    POSITIVE LOGITS
    -collapse
    0.30
     {{↵
    0.29
     fractional
    0.26
     [[[
    0.26
    /****************************************************************************↵
    0.26
    侥幸
    0.25
     fraction
    0.25
    çħ¦
    0.24
    管å±Ģ
    0.24
    ixin
    0.23
    Activations Density 15.268%

    No Known Activations