© 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. 24-TRANSCODER-HP
    7. 149638
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gather
    -0.30
    åIJĪ
    -0.25
     outside
    -0.25
    oard
    -0.25
    duce
    -0.25
     useful
    -0.24
    aksi
    -0.24
    ò
    -0.24
    неÑĨ
    -0.24
    /cs
    -0.24
    POSITIVE LOGITS
    符
    0.29
     watcher
    0.27
    .fm
    0.26
    ArrayOf
    0.26
    åĩºéģĵ
    0.25
    模ç³Ĭ
    0.24
    社ä¼ļåĮĸ
    0.24
    YY
    0.24
    导读
    0.23
    ADR
    0.23
    Activations Density 0.937%

    No Known Activations

    This feature has no known activations.