© 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. 111096
    Prev
    Next
    INDEX
    Explanations

    Hampton

    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
     cam
    -0.27
    amedi
    -0.26
    ims
    -0.24
     bons
    -0.24
    eri
    -0.23
    csi
    -0.23
    éĢģåĩº
    -0.23
     dough
    -0.23
    sem
    -0.23
    rait
    -0.23
    POSITIVE LOGITS
    Ĥæķ°
    0.26
    çľģ
    0.24
    çı¾
    0.24
    /projects
    0.24
    );;↵
    0.23
    annies
    0.23
    à¸Īà¸ļ
    0.23
    anny
    0.23
     editorial
    0.23
     Redistributions
    0.23
    Activations Density 0.002%

    No Known Activations