© 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. 113104
    Prev
    Next
    INDEX
    Explanations

    computers and governance

    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
     sidel
    -0.26
    ZN
    -0.26
    éŃij
    -0.26
    決ãĤģ
    -0.25
    º«
    -0.25
    arta
    -0.25
    çģĮ
    -0.24
    bole
    -0.24
    dden
    -0.24
    olith
    -0.24
    POSITIVE LOGITS
    !I
    0.28
    !*
    0.27
    !
    0.27
    !/
    0.27
     jail
    0.26
    ahr
    0.25
    æĪijçĪ±ä½ł
    0.25
     PRESS
    0.24
    !')↵↵
    0.24
    æīĵæĸŃ
    0.24
    Activations Density 0.001%

    No Known Activations