© 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. 131216
    Prev
    Next
    INDEX
    Explanations

    United

    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
    第ä¸ĢæŃ¥
    -0.27
    è¾ĪåŃIJ
    -0.25
    ulkan
    -0.25
    EMY
    -0.25
    åľ°æĸ¹
    -0.24
    lycer
    -0.24
    gram
    -0.24
    åŁºéĩij份é¢Ŀ
    -0.23
    ewhere
    -0.23
    (GLFW
    -0.23
    POSITIVE LOGITS
     Rand
    0.25
     Fires
    0.25
     Bomb
    0.25
    çĸı
    0.25
    raries
    0.25
     réfé
    0.24
     bare
    0.24
    -floor
    0.24
     Refer
    0.24
     Invent
    0.24
    Activations Density 0.097%

    No Known Activations