© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 89006
    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
    Negative Logits
    ä¸įäºĨ
    -0.31
    åİĤ
    -0.27
    åı¯æĢľ
    -0.25
    antom
    -0.24
    )s
    -0.24
    è¦ģçľĭ
    -0.24
    never
    -0.23
    —or
    -0.23
    å°½
    -0.23
     sleep
    -0.22
    POSITIVE LOGITS
    AEA
    0.28
     (~(
    0.26
     Edmonton
    0.24
     Urb
    0.24
    ánÃŃ
    0.24
    éķĿ
    0.23
    èĪĴ
    0.23
     Ames
    0.23
     modulus
    0.23
    ONG
    0.22
    Activations Density 0.022%

    No Known Activations

    This feature has no known activations.