© 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. 12-TRANSCODER-HP
    7. 24061
    Prev
    Next
    INDEX
    Explanations

    Technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å°¼äºļ
    -0.30
    ui
    -0.29
     model
    -0.28
    åĩºå¸Ńä¼ļè®®
    -0.28
    次ä¼ļè®®
    -0.28
    ID
    -0.28
     global
    -0.27
     GUI
    -0.27
    UI
    -0.26
    -
    -0.26
    POSITIVE LOGITS
    agrams
    0.29
    tery
    0.29
     RECT
    0.29
     <+
    0.29
    otypes
    0.29
    ä¸ĵ项èµĦéĩij
    0.28
    åħij
    0.28
     vegas
    0.28
     Naughty
    0.27
    æĪijåıĪ
    0.27
    Activations Density 0.016%

    No Known Activations