© 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. 111578
    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
    å°ijè§ģ
    -0.27
    otron
    -0.26
    大åݦ
    -0.26
    adows
    -0.26
    ëŀŃ
    -0.24
    تص
    -0.24
    çªĺ
    -0.24
    stad
    -0.23
    表çİ°
    -0.23
    建åĨĽ
    -0.23
    POSITIVE LOGITS
    .origin
    0.24
    ://${
    0.24
    fts
    0.23
    eve
    0.23
    leurs
    0.23
    第ä¸ĢæŶéĹ´
    0.22
    .ft
    0.22
     highlights
    0.22
    -ft
    0.22
    åİŁä»¶
    0.22
    Activations Density 0.130%

    No Known Activations

    This feature has no known activations.