© 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. 9-TRANSCODER-HP
    7. 29889
    Prev
    Next
    INDEX
    Explanations

    contract

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    енÑĮ
    -0.28
    å¤įåį°
    -0.26
    ç¼Ĺ
    -0.25
    æĢ»çļĦæĿ¥è¯´
    -0.25
     Hire
    -0.24
    ATAR
    -0.24
     Slash
    -0.24
    æľº
    -0.24
    .hw
    -0.24
    æľºåŀĭ
    -0.24
    POSITIVE LOGITS
     bag
    0.29
    zM
    0.28
    Bag
    0.26
     Bags
    0.26
    osate
    0.25
    _bag
    0.25
    LayoutPanel
    0.25
     Bag
    0.25
    æ®ĥ
    0.24
    bag
    0.24
    Activations Density 0.207%

    No Known Activations