© 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. 149693
    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
    å¸ij
    -0.32
     cray
    -0.30
     capitalize
    -0.30
     switch
    -0.28
     escalate
    -0.27
    ç´¢èµĶ
    -0.27
    idl
    -0.26
    cone
    -0.26
    åĪĩæį¢
    -0.26
    lig
    -0.25
    POSITIVE LOGITS
    ulus
    0.32
    æĪ·å¤ĸ
    0.26
    åºŃéĻ¢
    0.26
    ç«ij
    0.26
    phe
    0.26
    >Title
    0.25
     outdoors
    0.25
    íķĢ
    0.24
    .tmp
    0.24
    è¯Ħ论
    0.24
    Activations Density 0.237%

    No Known Activations

    This feature has no known activations.