© 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. 130212
    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
    åĽ½ç½ij
    -0.28
    ort
    -0.26
     ‘
    -0.26
     blades
    -0.25
    _clone
    -0.25
    Clone
    -0.24
    éĢīçĶ¨
    -0.24
    .task
    -0.23
    ardi
    -0.23
    é£İåı£
    -0.23
    POSITIVE LOGITS
    çĭ¬ä¸ĢæĹłäºĮ
    0.28
    anja
    0.26
    SELF
    0.26
    é¦Ĩ
    0.26
    SPAN
    0.26
    æݨæµĭ
    0.25
    示æĦı
    0.25
    è±¢
    0.25
    ndx
    0.24
    ç¥Ī
    0.24
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.