© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 212
    Prev
    Next
    INDEX
    Explanations

    -level

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addle
    -0.28
    NewLabel
    -0.24
    pac
    -0.23
    ouncements
    -0.23
    zan
    -0.23
    ificio
    -0.23
    浦
    -0.23
    æĸ°è¥¿
    -0.23
    æīĵåĵį
    -0.22
    ạn
    -0.22
    POSITIVE LOGITS
    igos
    0.25
    rie
    0.24
    åı±
    0.24
    iel
    0.24
    mium
    0.23
    ãģ¾
    0.23
    ivity
    0.23
     bó
    0.23
    uset
    0.23
     Guinness
    0.23
    Activations Density 0.094%

    No Known Activations