© 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. 130554
    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
     makeStyles
    -0.27
    amics
    -0.26
    俳
    -0.24
    ä¸įå±ij
    -0.23
    åĸľæ¬¢åIJĥ
    -0.22
    è¸Į
    -0.22
    amen
    -0.22
    lashes
    -0.22
     Clears
    -0.22
    å¿ĥ缮
    -0.22
    POSITIVE LOGITS
    大åİħ
    0.24
    åĮºæĶ¿åºľ
    0.24
    иÑı
    0.24
    çIJ¼
    0.24
     BASIS
    0.23
     slam
    0.23
     interchangeable
    0.23
    æĢ»ä»·
    0.23
    aza
    0.23
    éĤ£ä¹Ī容æĺĵ
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.