© 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. 88086
    Prev
    Next
    INDEX
    Explanations

    Measurement and quantification

    np_max-act · gemini-2.0-flash
    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
     dependent
    -0.31
     depend
    -0.27
     depended
    -0.27
     Twig
    -0.27
     vids
    -0.26
     relied
    -0.26
    éĿł
    -0.26
    -Token
    -0.26
    ä¾Ŀèµĸ
    -0.25
     complexity
    -0.25
    POSITIVE LOGITS
    caffe
    0.27
    主ä¹īèĢħ
    0.27
    主ä¹ī
    0.27
    mnop
    0.26
    .microsoft
    0.26
    izes
    0.25
    _On
    0.25
    çİĩ为
    0.24
    mn
    0.24
    ANNER
    0.23
    Activations Density 0.011%

    No Known Activations