© 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. 22-TRANSCODER-HP
    7. 112694
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĮ¿
    -0.27
    交ä»ĺ
    -0.26
    jeta
    -0.26
    ä»Ģä¹Īæĺ¯
    -0.26
     hung
    -0.25
    对ç«ĭ
    -0.25
    _Em
    -0.25
    ç°¿
    -0.25
    .pt
    -0.24
     Joy
    -0.24
    POSITIVE LOGITS
    logen
    0.29
    rogen
    0.28
    elah
    0.27
    ersen
    0.27
    çĶµåİĤ
    0.26
    District
    0.26
    央ä¼ģ
    0.26
    зов
    0.24
    _district
    0.24
    æĢ»çIJĨ
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.