© 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. 25-TRANSCODER-HP
    7. 108716
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.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¥īçĮ®
    -0.27
     fur
    -0.25
    virt
    -0.25
     squirt
    -0.24
    çĶŁæķĪ
    -0.24
    åħ¥èģĮ
    -0.24
    opers
    -0.24
    Markers
    -0.24
    åľĪ
    -0.23
    åĪ°è¾¾
    -0.23
    POSITIVE LOGITS
    .removeChild
    0.27
    åħ®
    0.25
    æŃĮ
    0.24
     integr
    0.24
    utt
    0.24
     vé
    0.24
     templates
    0.24
    hyth
    0.24
    ayah
    0.23
    çļĦç¾İ好
    0.23
    Activations Density 0.137%

    No Known Activations

    This feature has no known activations.