© 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. 112922
    Prev
    Next
    INDEX
    Explanations

    Code or system logs

    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
    zens
    -0.29
    tees
    -0.27
    odie
    -0.25
    isChecked
    -0.25
     screened
    -0.24
    /MIT
    -0.24
     IOS
    -0.24
    ajo
    -0.24
    ISTER
    -0.23
    asti
    -0.23
    POSITIVE LOGITS
     dit
    0.27
    ata
    0.25
    管家
    0.24
    è¿ĩäºĨ
    0.24
    ava
    0.24
    0.23
    åı¸ä»¤
    0.23
     pro
    0.23
     cr
    0.23
     Dit
    0.23
    Activations Density 0.073%

    No Known Activations