© 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. 22-TRANSCODER-HP
    7. 88390
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elage
    -0.25
    ernaut
    -0.25
     tslib
    -0.24
    strip
    -0.24
    äºİ
    -0.24
    еÑģÑĤв
    -0.23
    åİĭåĬĽ
    -0.23
     anchored
    -0.23
     NaN
    -0.23
     GLsizei
    -0.23
    POSITIVE LOGITS
    åĩŃ
    0.28
    !↵↵↵↵
    0.27
    æĨij
    0.26
     Velvet
    0.25
     invent
    0.25
    eda
    0.25
    éļ¶å±ŀ
    0.25
    对该
    0.24
     shining
    0.24
    assy
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.