© 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. 108505
    Prev
    Next
    INDEX
    Explanations

    Generic text

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æ³ķå®ļ
    -0.52
     legal
    -0.43
     regulations
    -0.43
    æ³ķè§Ħ
    -0.42
     allowed
    -0.40
    è§Ħå®ļ
    -0.40
     national
    -0.39
     mandatory
    -0.38
     mandated
    -0.37
    èµĦæł¼
    -0.36
    POSITIVE LOGITS
    InnerHTML
    0.28
    Raised
    0.27
    [model
    0.26
     Philly
    0.26
     metaph
    0.26
    人æ°Ķ
    0.25
    空åīį
    0.25
    empor
    0.25
     Enemies
    0.25
    [parent
    0.25
    Activations Density 70.318%

    No Known Activations