© 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. 30183
    Prev
    Next
    INDEX
    Explanations

    first

    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
    ocre
    -0.28
    assen
    -0.27
    å¿ĥè·³
    -0.27
    -Cs
    -0.25
    orous
    -0.25
    aeda
    -0.25
    èĥĿ
    -0.25
    xec
    -0.24
    anked
    -0.24
     Хо
    -0.24
    POSITIVE LOGITS
    ite
    0.27
    goog
    0.26
     cond
    0.24
    ites
    0.24
     **
    0.24
     Candy
    0.24
    hed
    0.24
    iku
    0.24
    paths
    0.24
    edReader
    0.23
    Activations Density 3.198%

    No Known Activations