© 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. 29294
    Prev
    Next
    INDEX
    Explanations

    oxide

    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
    åıĮéĩį
    -0.26
    icates
    -0.26
    èĦ¾
    -0.25
    eth
    -0.25
    lez
    -0.25
    heat
    -0.24
    anz
    -0.24
    .createCell
    -0.24
    poses
    -0.24
    çĥŃ线
    -0.24
    POSITIVE LOGITS
    olib
    0.29
    ALSE
    0.28
    OE
    0.27
     designation
    0.26
    erset
    0.26
     radius
    0.26
     sabot
    0.25
    æŃ¥è¡Į
    0.25
     Wich
    0.25
     Scal
    0.24
    Activations Density 1.082%

    No Known Activations