© 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. 109035
    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
    inputEmail
    -0.28
    åĬłä¸Ĭ
    -0.25
     referring
    -0.25
    èĢ¨
    -0.25
    ç³ł
    -0.24
    çļĦéĩįçĤ¹
    -0.24
    èģĶç³»æĪij们
    -0.24
    ниÑĨÑĭ
    -0.24
     score
    -0.23
    çĤ¹åĩ»æŁ¥çľĭ
    -0.23
    POSITIVE LOGITS
    京åŁİ
    0.28
    zelf
    0.25
    клÑİÑĩи
    0.25
    esture
    0.25
    ucle
    0.25
    overs
    0.25
    æİı
    0.24
    å¤ĸæı´
    0.24
    ()["
    0.24
    大èħ¿
    0.24
    Activations Density 0.119%

    No Known Activations

    This feature has no known activations.