© 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. 99205
    Prev
    Next
    INDEX
    Explanations

    puppet pups

    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
    imuth
    -0.28
    washer
    -0.27
    ider
    -0.25
    LY
    -0.25
    VILLE
    -0.24
    udden
    -0.24
    indows
    -0.24
    沫
    -0.24
     Chall
    -0.24
    leton
    -0.24
    POSITIVE LOGITS
    asty
    0.28
    :@
    0.27
    alf
    0.26
    ----↵↵
    0.25
    ,...↵↵
    0.25
    alen
    0.24
    ....↵↵
    0.24
    ları
    0.24
    ,...↵
    0.24
    人为
    0.24
    Activations Density 0.078%

    No Known Activations