© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 29818
    Prev
    Next
    INDEX
    Explanations

    key

    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
    Not in Any Lists

    No Comments

    Negative Logits
    çıŃ
    -0.29
    Ñĥг
    -0.28
     fle
    -0.28
    jem
    -0.28
    缴æµģ
    -0.27
    å¤ĩçĶ¨
    -0.26
    trap
    -0.26
    éĴ¢çŃĭ
    -0.26
     sj
    -0.25
    çıŃ级
    -0.25
    POSITIVE LOGITS
    cko
    0.27
    lation
    0.27
    kee
    0.26
     IMAGES
    0.26
     gek
    0.25
     Upper
    0.24
     spons
    0.24
     Kirst
    0.24
    perm
    0.24
     feeds
    0.24
    Activations Density 1.599%

    No Known Activations