© 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. 31-TRANSCODER-HP
    7. 19727
    Prev
    Next
    INDEX
    Explanations

    linear

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ert
    -0.27
     cur
    -0.27
     cogn
    -0.26
    emon
    -0.26
    кÑĥ
    -0.26
     pose
    -0.25
     cái
    -0.25
     audible
    -0.25
    é¦
    -0.25
    WER
    -0.25
    POSITIVE LOGITS
    onis
    0.29
     equations
    0.28
    åħ¬å¹³
    0.28
     regression
    0.27
    bucks
    0.26
    å¹³åı°
    0.26
    -platform
    0.25
    platform
    0.25
     Regression
    0.24
    ãĥĹãĥ©ãĥ³
    0.24
    Activations Density 0.142%

    No Known Activations