© 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. 9378
    Prev
    Next
    INDEX
    Explanations

    eating/feeding

    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
    isoft
    -0.29
    worm
    -0.29
    cratch
    -0.28
    PAL
    -0.28
    apult
    -0.26
     ster
    -0.25
    hiba
    -0.25
    -result
    -0.24
     petals
    -0.24
    é©¿
    -0.24
    POSITIVE LOGITS
     feeding
    0.42
    è¿Ľé£Ł
    0.39
     feed
    0.37
    åIJĥçļĦ
    0.36
     fed
    0.34
     drinking
    0.34
     Eating
    0.33
     eating
    0.32
    åIJ¸
    0.32
     feeds
    0.32
    Activations Density 0.020%

    No Known Activations