© 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. 8911
    Prev
    Next
    INDEX
    Explanations

    medical or scientific research

    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
     fat
    -0.38
    æ²¹
    -0.34
    -fat
    -0.34
     fats
    -0.34
     oil
    -0.33
    èĦĤ
    -0.32
    æĢł
    -0.31
    fat
    -0.30
    oil
    -0.29
    èĦĤèĤª
    -0.29
    POSITIVE LOGITS
     pen
    0.31
    pen
    0.30
    éĢıæĺİ
    0.28
     Nur
    0.27
    Pen
    0.26
    eward
    0.26
    CustomAttributes
    0.26
     transparency
    0.26
    æłĩ
    0.25
    .uri
    0.25
    Activations Density 0.009%

    No Known Activations