© 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. 108803
    Prev
    Next
    INDEX
    Explanations

    /

    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
     Shr
    -0.25
     Presence
    -0.25
     presence
    -0.25
    çļĦ形象
    -0.24
    areth
    -0.24
     Via
    -0.24
    abal
    -0.24
    presence
    -0.24
    寤
    -0.24
    æ¼Ķ
    -0.23
    POSITIVE LOGITS
    íĶ½
    0.28
    å¾Īå¤ļ
    0.27
    è¿ŀäºij
    0.26
     drove
    0.26
    åŀĤ
    0.26
    utra
    0.26
    ноÑģ
    0.26
    è°Į
    0.25
    åµ´
    0.25
    å¤ļäºĨ
    0.24
    Activations Density 1.747%

    No Known Activations