© 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. 29196
    Prev
    Next
    INDEX
    Explanations

    geographic locations

    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
    automation
    -0.32
     destiny
    -0.28
    alty
    -0.27
    åı£æ°´
    -0.27
    对åħ¶
    -0.26
    æĦŁåħ´è¶£
    -0.25
     mun
    -0.25
     pylint
    -0.24
    nda
    -0.24
     maç
    -0.24
    POSITIVE LOGITS
    elsius
    0.28
    èĬ³é¦Ļ
    0.28
    élé
    0.25
    -initialized
    0.24
    actly
    0.23
    .generated
    0.23
     WARRANTIES
    0.23
    ãģĦãĤĭãģ¨
    0.23
    inel
    0.23
    /TR
    0.23
    Activations Density 0.710%

    No Known Activations