© 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. 88895
    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
    LESS
    -0.28
    less
    -0.28
     payday
    -0.25
    imos
    -0.25
     consciousness
    -0.24
    ono
    -0.24
     conscious
    -0.24
    uj
    -0.24
    hus
    -0.23
    第äºĶ
    -0.23
    POSITIVE LOGITS
     besie
    0.25
    pipes
    0.24
    åįģæĿ¡
    0.24
    æ¸ħåĩĢ
    0.24
     confer
    0.24
    ÑģÑĤвоваÑĤÑĮ
    0.24
    indr
    0.24
     cater
    0.23
    боÑĢ
    0.23
    InView
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.