© 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. 9-TRANSCODER-HP
    7. 29337
    Prev
    Next
    INDEX
    Explanations

    Disconnected text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Mitt
    -0.26
    anto
    -0.26
    ä»Ĭ天çļĦ
    -0.26
     Geh
    -0.25
    左边
    -0.25
     subdued
    -0.24
    attles
    -0.24
    enburg
    -0.24
    åķ
    -0.24
    ä¸ĢåĪĩ
    -0.24
    POSITIVE LOGITS
    åĪ»çĶ»
    0.26
     "<<
    0.26
    åĽ¾ä¸º
    0.26
    Äįe
    0.25
    äºĨ许å¤ļ
    0.25
    详æĥħ
    0.25
    ublished
    0.25
    RowAt
    0.25
     Independ
    0.25
    que
    0.24
    Activations Density 1.247%

    No Known Activations