© 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. 20-TRANSCODER-HP
    7. 108773
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ADM
    -0.29
     suit
    -0.28
    大æī¹
    -0.28
    æĢĢæĬ±
    -0.27
    æ±ĤåĬ©
    -0.27
    表çİ°åĩº
    -0.26
    è¯ī
    -0.26
    ACP
    -0.25
     wreak
    -0.25
     frequencies
    -0.24
    POSITIVE LOGITS
    æł¼
    0.27
    æ¯ıä¸Ģä½į
    0.25
    arest
    0.25
    gran
    0.25
     logic
    0.25
    åĨįéĢł
    0.25
    .async
    0.24
    ]].
    0.24
    LAY
    0.24
    arters
    0.24
    Activations Density 22.745%

    No Known Activations