© 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. 129148
    Prev
    Next
    INDEX
    Explanations

    ank

    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
    htub
    -0.32
     Bij
    -0.29
    gien
    -0.29
    çļĦåķĨåĵģ
    -0.28
    ikal
    -0.27
    们éĥ½
    -0.26
    iken
    -0.25
     decl
    -0.25
    uchos
    -0.24
     Declarations
    -0.24
    POSITIVE LOGITS
     matter
    0.26
    wer
    0.26
    owed
    0.26
    ãģĦãģŁ
    0.25
    onas
    0.25
    isplay
    0.24
    traffic
    0.24
    enn
    0.24
    åĽ¢éķ¿
    0.24
    ledge
    0.23
    Activations Density 0.017%

    No Known Activations