© 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. 22-TRANSCODER-HP
    7. 111988
    Prev
    Next
    INDEX
    Explanations

    make

    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
    Not in Any Lists

    No Comments

    Negative Logits
     openings
    -0.29
     what
    -0.27
    çķ
    -0.25
    åľ¨åĵªéĩĮ
    -0.24
     immediate
    -0.24
    EndInit
    -0.24
    åįŀ
    -0.24
     opening
    -0.24
     ob
    -0.24
    igi
    -0.24
    POSITIVE LOGITS
    æĪIJ为ä¸ŃåĽ½
    0.27
    å²ģ以ä¸Ĭ
    0.26
    profiles
    0.26
    åħ·æľīèī¯å¥½
    0.25
    cce
    0.25
    zet
    0.25
    éªĸ
    0.25
    两款
    0.24
     sposób
    0.24
     Plates
    0.24
    Activations Density 0.017%

    No Known Activations