© 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. 88993
    Prev
    Next
    INDEX
    Explanations

    minimize

    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
    bidden
    -0.26
    æıIJçİ°
    -0.25
     dak
    -0.24
    ammers
    -0.24
     mặt
    -0.24
     Pear
    -0.23
    ("$.
    -0.23
    好åIJ§
    -0.23
    æĭĽåij¼
    -0.23
    ç»Ĩç»Ĩ
    -0.23
    POSITIVE LOGITS
    erva
    0.27
    /max
    0.25
    embro
    0.24
     sized
    0.24
     impact
    0.24
    impact
    0.24
    atur
    0.24
    Overall
    0.24
     wrap
    0.24
    -rights
    0.23
    Activations Density 0.169%

    No Known Activations