© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8045
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    á»ı
    -0.26
    CHAN
    -0.25
    è´Ŀ
    -0.24
    akedown
    -0.24
     inner
    -0.23
     work
    -0.23
    Cou
    -0.23
    å·¥åķĨ
    -0.23
     Inner
    -0.23
     Coupons
    -0.23
    POSITIVE LOGITS
    èĩĨ
    0.27
    night
    0.27
    ramer
    0.25
    寧
    0.24
    zM
    0.23
    oins
    0.23
    ÑĤок
    0.23
    红æĹĹ
    0.23
     esk
    0.23
    ØŃر
    0.23
    Activations Density 0.061%

    No Known Activations

    This feature has no known activations.