© 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. 55
    Prev
    Next
    INDEX
    Explanations

    Corruption

    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
    çħ¤çŁ¿
    -0.28
    æĸ°åŀĭ
    -0.27
    asive
    -0.27
    however
    -0.27
    æīĢè°ĵçļĦ
    -0.27
    年产
    -0.26
     however
    -0.26
    ambi
    -0.25
    emachine
    -0.25
    amba
    -0.24
    POSITIVE LOGITS
    IDL
    0.30
     Administr
    0.26
     conspir
    0.25
     administr
    0.25
    bidden
    0.25
    aal
    0.25
    .sz
    0.25
     rep
    0.25
     bü
    0.24
    лан
    0.24
    Activations Density 0.020%

    No Known Activations