© 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. 109412
    Prev
    Next
    INDEX
    Explanations

    "in view of" or "in light of"

    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
    .bmp
    -0.28
    nell
    -0.27
    -placeholder
    -0.27
    nh
    -0.26
    (savedInstanceState
    -0.26
     hell
    -0.26
     requestOptions
    -0.26
    ÑĨикл
    -0.25
    è¦ģçľĭ
    -0.25
    elm
    -0.25
    POSITIVE LOGITS
     Powerful
    0.26
     underlying
    0.25
     powerful
    0.25
    èĥĮæĻ¯ä¸ĭ
    0.25
     Lonely
    0.25
    abs
    0.24
     unlikely
    0.24
     пÑĢоизведен
    0.24
     Remark
    0.24
     Abs
    0.23
    Activations Density 0.226%

    No Known Activations