© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 88981
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    uyến
    -0.27
    åħ¨æł¡
    -0.27
     conversation
    -0.26
     Tart
    -0.26
     ↵		↵
    -0.25
    бав
    -0.24
    ạm
    -0.24
     calendar
    -0.24
     conversations
    -0.24
     loosely
    -0.24
    POSITIVE LOGITS
    家ä¼Ļ
    0.27
    ECH
    0.27
    afil
    0.27
    ftype
    0.26
    ataka
    0.25
    retch
    0.25
    åıĹå½±åĵį
    0.24
    förder
    0.24
     contrat
    0.24
    ä»ĺè´¹
    0.24
    Activations Density 0.004%

    No Known Activations