© 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. 35-TRANSCODER-HP
    7. 38793
    Prev
    Next
    INDEX
    Explanations

    Az

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    pi
    -0.29
    (Person
    -0.28
    nn
    -0.28
    umbo
    -0.27
    yled
    -0.26
    illes
    -0.25
    fig
    -0.25
    min
    -0.25
    nis
    -0.25
    .pl
    -0.25
    POSITIVE LOGITS
    Az
    0.32
     Az
    0.32
     AZ
    0.30
    azo
    0.30
    azi
    0.29
     az
    0.29
    AZ
    0.29
     azimuth
    0.28
    asses
    0.28
    ASSES
    0.28
    Activations Density 7.059%

    No Known Activations