© 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. 33-TRANSCODER-HP
    7. 53015
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç³ķ
    -0.27
    ler
    -0.27
     Throne
    -0.26
    acle
    -0.25
    edith
    -0.25
     thousand
    -0.24
    ccoli
    -0.24
    arta
    -0.24
    airo
    -0.24
    isable
    -0.23
    POSITIVE LOGITS
     //↵
    0.29
    LOB
    0.28
    sz
    0.27
    öm
    0.27
    å·¡è§Ĩ
    0.26
     //č↵
    0.25
    å·¡åĽŀ
    0.25
     ///↵
    0.25
     K
    0.25
    bel
    0.24
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.