© 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. 97299
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    igner
    -0.24
     Poll
    -0.24
    ãģ¾ãģķ
    -0.24
     poll
    -0.23
    Poll
    -0.23
    .Directory
    -0.23
     scenario
    -0.23
     augment
    -0.23
    迹
    -0.23
     autos
    -0.23
    POSITIVE LOGITS
    [new
    0.26
    ä¼ĺ
    0.24
    çĤ¹åĩ»æŁ¥çľĭ
    0.24
    津贴
    0.23
    æĹĥ
    0.23
    _tac
    0.22
    çĨŁ
    0.22
    ellow
    0.22
    åıĤ
    0.22
    usk
    0.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.