© 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. 140916
    Prev
    Next
    INDEX
    Explanations

    code

    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
    arna
    -0.28
    对æĪij们
    -0.28
     TER
    -0.28
    .ide
    -0.27
    对ä»ĸ们
    -0.27
    å¼¹
    -0.26
    对ä¼ģä¸ļ
    -0.26
     backs
    -0.25
    对
    -0.24
    edd
    -0.24
    POSITIVE LOGITS
    StateMachine
    0.27
    rijk
    0.27
     born
    0.26
    éļľ
    0.25
    COVER
    0.25
    ç²Ĺç³Ļ
    0.24
    à¸Ħร
    0.24
    yer
    0.24
    çĭĢ
    0.23
    æ®ĸ
    0.23
    Activations Density 32.509%

    No Known Activations