© 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. 25-TRANSCODER-HP
    7. 109578
    Prev
    Next
    INDEX
    Explanations

    Code and random text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    edia
    -0.31
    agem
    -0.27
    -scroll
    -0.27
    ä»Ģä¹Īäºĭ
    -0.27
    .Rendering
    -0.26
    -mouth
    -0.26
    å¿Į
    -0.26
    ละà¸Ħร
    -0.25
    -than
    -0.25
    iete
    -0.25
    POSITIVE LOGITS
    dur
    0.33
    dens
    0.27
    ä¸į足以
    0.26
    False
    0.26
    åľ¨è¿ĩ渡
    0.26
    arg
    0.26
    false
    0.25
    .arg
    0.25
     pay
    0.25
     false
    0.25
    Activations Density 0.056%

    No Known Activations