© 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. 18-TRANSCODER-HP
    7. 88545
    Prev
    Next
    INDEX
    Explanations

    news articles, documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trách
    -0.31
    éģĹçķĻ
    -0.28
    责任
    -0.28
    æķĻè®Ń
    -0.28
    失误
    -0.27
    hait
    -0.27
     accidental
    -0.26
     Responsibility
    -0.26
     inadvert
    -0.26
    ç«ĭæ³ķ
    -0.26
    POSITIVE LOGITS
     Benson
    0.27
    -TV
    0.27
    ivo
    0.25
    ha
    0.25
    -touch
    0.25
    appro
    0.25
    EMS
    0.24
    _semaphore
    0.24
     Illustrated
    0.24
     ITER
    0.24
    Activations Density 14.931%

    No Known Activations