© 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. 111268
    Prev
    Next
    INDEX
    Explanations

    Code/markup

    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
    Not in Any Lists

    No Comments

    Negative Logits
    roads
    -0.26
     sentinel
    -0.25
    ãĤĭãĤĪãģĨãģ«
    -0.25
    öz
    -0.25
    stin
    -0.25
    pekt
    -0.24
    пÑĥÑĤ
    -0.24
    å¤įæĿĤ
    -0.24
    ÙĦÙħ
    -0.24
     resonate
    -0.23
    POSITIVE LOGITS
    å¦ĤæŀľæĤ¨
    0.46
    èĭ¥æĤ¨
    0.41
     optional
    0.40
    å¦Ĥæŀľä½ł
    0.38
    å¦Ĥæŀľä½łæĥ³
    0.37
    optional
    0.36
     if
    0.36
    å¦Ĥæŀľ
    0.36
     If
    0.35
     nếu
    0.34
    Activations Density 0.016%

    No Known Activations