© 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. 20-TRANSCODER-HP
    7. 141916
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itionally
    -0.27
    ême
    -0.26
     má»ıi
    -0.26
    émon
    -0.25
    öm
    -0.24
    igue
    -0.24
    -clear
    -0.24
    ında
    -0.24
    ,âĢ¦↵↵
    -0.24
    rô
    -0.24
    POSITIVE LOGITS
    Inf
    0.31
     Inf
    0.29
    姹
    0.28
    å°¼äºļ
    0.28
    鼷
    0.28
    obj
    0.27
    á»įng
    0.25
    MLE
    0.25
     Si
    0.24
    éĵ§
    0.24
    Activations Density 24.009%

    No Known Activations

    This feature has no known activations.