© 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. 23-TRANSCODER-HP
    7. 24711
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amat
    -0.27
    ç²±
    -0.27
    ibrator
    -0.27
    å¹£
    -0.25
    ç»ıåİĨäºĨ
    -0.25
     Vibr
    -0.25
     ready
    -0.24
    пиÑģание
    -0.23
    -reader
    -0.23
    -budget
    -0.23
    POSITIVE LOGITS
    åĭĺæİ¢
    0.26
    æī¿åĬŀ
    0.26
    说
    0.26
    çĿĢçľ¼
    0.25
     bott
    0.24
     rol
    0.24
     Wonderland
    0.24
     pal
    0.24
    äºij端
    0.23
    .nan
    0.23
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.