© 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. 129023
    Prev
    Next
    INDEX
    Explanations

    your

    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
    aut
    -0.29
    rott
    -0.26
    æĹ¥èµ·
    -0.25
     Ngo
    -0.25
    æĪ´çĿĢ
    -0.25
    åķĨä¸ļåĮĸ
    -0.25
    anth
    -0.24
    rong
    -0.24
    Version
    -0.24
     kans
    -0.23
    POSITIVE LOGITS
    èĬ¬
    0.29
    æĸ°éĹ»ä¸Ńå¿ĥ
    0.26
    _increment
    0.25
    зал
    0.25
    ä¸ĭéĿ¢å°±
    0.25
     pes
    0.24
    )._
    0.23
    éĵºè®¾
    0.23
    :both
    0.23
    æķĻèĤ²èµĦæºIJ
    0.23
    Activations Density 0.008%

    No Known Activations