© 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. 111051
    Prev
    Next
    INDEX
    Explanations

    technical/academic writing

    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
    年人
    -0.32
    matic
    -0.28
    ombie
    -0.28
    enus
    -0.26
     dequeue
    -0.25
    acht
    -0.24
    dated
    -0.24
    oom
    -0.24
    xm
    -0.23
    ált
    -0.23
    POSITIVE LOGITS
     manually
    0.26
    lec
    0.26
    ivid
    0.26
    å·Ŀ
    0.25
    åı±
    0.24
    缸åıį
    0.24
    lep
    0.23
     ÑĪ
    0.23
     long
    0.23
    æĪijçľĭ
    0.23
    Activations Density 0.012%

    No Known Activations