© 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. 27-TRANSCODER-HP
    7. 57494
    Prev
    Next
    INDEX
    Explanations

    improvements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æł¡
    -0.27
    éĻ²
    -0.26
    fix
    -0.25
     Dining
    -0.25
    å¹¢
    -0.25
     kB
    -0.25
    åIJĥå®Į
    -0.24
    oney
    -0.24
    åĨĻåŃĹ楼
    -0.24
    士
    -0.24
    POSITIVE LOGITS
     improved
    0.35
     better
    0.34
     improvements
    0.31
    æĽ´å¥½çļĦ
    0.31
     improving
    0.30
     advances
    0.29
    avra
    0.29
     mejor
    0.29
     direct
    0.29
    æĶ¹åĸĦ
    0.28
    Activations Density 0.009%

    No Known Activations