© 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. 20-TRANSCODER-HP
    7. 130982
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    导读
    -0.26
    eria
    -0.25
    çĸĹæ³ķ
    -0.25
    åıįä¹ĭ
    -0.25
    é«ĺçŃīæķĻèĤ²
    -0.24
     therapy
    -0.24
    .currentState
    -0.24
    amil
    -0.24
     >&
    -0.23
    _CPP
    -0.23
    POSITIVE LOGITS
    å®
    0.32
    æĹ©æĻ¨
    0.30
    äºĶåĽĽ
    0.28
     Rest
    0.28
    ç»ħ
    0.27
    Rest
    0.25
    lying
    0.25
    hood
    0.25
    ä»įå°Ĩ
    0.25
    æµĥ
    0.24
    Activations Density 22.331%

    No Known Activations