© 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. 29781
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings

    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
     other
    -0.28
    åı¦ä¸Ģç§į
    -0.26
     op
    -0.26
    æĸ¹è¨Ģ
    -0.26
     operation
    -0.25
     contr
    -0.25
    op
    -0.25
    æĭĽ
    -0.24
    zenia
    -0.24
    æ¯ķ
    -0.24
    POSITIVE LOGITS
    èĦī
    0.27
    uhl
    0.26
    nç
    0.26
     ÑģооÑĤвеÑĤ
    0.26
    OI
    0.25
    åĨ²
    0.25
    åıĸåĨ³
    0.25
    "title
    0.25
     Stateless
    0.24
     (↵↵
    0.24
    Activations Density 2.222%

    No Known Activations