© 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. 98676
    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
    æľīæ¯Ĵ
    -0.27
    å±ī
    -0.26
     Gos
    -0.26
    çħ§æĸĻ
    -0.26
     Tob
    -0.25
    еÑī
    -0.25
    æģ°æģ°
    -0.24
     nearest
    -0.24
    .closest
    -0.24
    unsch
    -0.23
    POSITIVE LOGITS
    çĶŁ
    0.27
    ÃĮ
    0.26
    anner
    0.25
    yen
    0.25
    /Register
    0.25
    èµĦ
    0.25
    è¡Ģ
    0.25
    edi
    0.24
    ippi
    0.24
    ikel
    0.24
    Activations Density 0.034%

    No Known Activations

    This feature has no known activations.