© 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. 151016
    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
     airs
    -0.29
     specifier
    -0.27
    å©Ĩ
    -0.26
    Backdrop
    -0.26
     Herc
    -0.25
    å°§
    -0.25
     overwhelm
    -0.25
    works
    -0.24
    presso
    -0.24
    owell
    -0.24
    POSITIVE LOGITS
    zen
    0.28
    ÃŃculo
    0.27
    ä¸įéĢļ
    0.27
    drv
    0.26
     Identity
    0.25
    atures
    0.25
    +xml
    0.25
    åıĪä¸Ģ次
    0.25
    mund
    0.25
    æķĻåŃ¦è´¨éĩı
    0.25
    Activations Density 0.119%

    No Known Activations

    This feature has no known activations.