© 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. 29114
    Prev
    Next
    INDEX
    Explanations

    dielectrics and electricity

    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
    ç½ijé¦ĸ页
    -0.28
    ibern
    -0.28
     Affero
    -0.27
    unge
    -0.26
    ç¼ĵåĨ²
    -0.26
    aits
    -0.26
    idden
    -0.26
    omen
    -0.25
    chten
    -0.25
    åĪĨå±Ģ
    -0.25
    POSITIVE LOGITS
    æĸĹäºī
    0.29
    æĪĺæĸĹ
    0.27
     cond
    0.27
    letion
    0.27
     block
    0.27
    block
    0.26
    look
    0.26
    ç»®
    0.26
    battle
    0.26
    Block
    0.25
    Activations Density 0.446%

    No Known Activations