© 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. 112644
    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
    orns
    -0.29
    ä¸Ģç»ı
    -0.26
     VL
    -0.26
    æĮł
    -0.26
    åıŃ
    -0.25
    稷
    -0.25
    desk
    -0.25
    éĵij
    -0.25
     Vit
    -0.24
    ä¹³ä¸ļ
    -0.24
    POSITIVE LOGITS
    ModelState
    0.29
    åºĹéĩĮ
    0.28
     compens
    0.27
    enberg
    0.27
    uden
    0.27
    -trade
    0.26
    asar
    0.26
     FUN
    0.25
    è°Ī
    0.25
    åºĹ
    0.24
    Activations Density 0.035%

    No Known Activations

    This feature has no known activations.