© 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. 129908
    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
     Tr
    -0.28
     short
    -0.26
    Tr
    -0.26
     tr
    -0.25
     shorter
    -0.24
    rish
    -0.24
    çĨŁ
    -0.24
    è¦ģåľ¨
    -0.23
    tr
    -0.23
     simple
    -0.23
    POSITIVE LOGITS
     trụ
    0.28
     nominated
    0.25
    åħ³éŨ
    0.25
    åij½åIJį
    0.24
    olem
    0.24
    纸ä¸Ĭ
    0.24
    å¼ĢéŨ
    0.23
     jewellery
    0.23
     gearbox
    0.23
    KeyName
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.