© 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. 29124
    Prev
    Next
    INDEX
    Explanations

    to

    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
    ered
    -0.28
    umont
    -0.25
    agara
    -0.25
    ",[
    -0.25
    ipl
    -0.24
    ONA
    -0.24
    ipline
    -0.24
    åĿļåĽº
    -0.24
    åĮºåŁŁåĨħ
    -0.24
    .fhir
    -0.24
    POSITIVE LOGITS
    üc
    0.30
    ä¾Ľ
    0.27
     tet
    0.27
    å®ŀæĸ½æĦıè§ģ
    0.27
    uman
    0.25
     emotion
    0.24
    ðŁĺİ
    0.24
     ie
    0.24
     imp
    0.24
    frm
    0.24
    Activations Density 0.308%

    No Known Activations