© 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. 142434
    Prev
    Next
    INDEX
    Explanations

    descriptions and analyses

    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
    è¡°
    -0.43
     decreasing
    -0.42
     diminishing
    -0.41
    ¡°
    -0.40
     fading
    -0.36
     declining
    -0.34
    åĩıå¼±
    -0.34
     lesser
    -0.34
     decrease
    -0.33
    éĢĢ
    -0.33
    POSITIVE LOGITS
    çļĦ表çİ°
    0.29
    åħ³éĶ®æŶåĪ»
    0.28
    olith
    0.26
    ä¸įåIJĥ
    0.25
    å¤ĩæĪĺ
    0.25
    жен
    0.25
     conflict
    0.25
    FileSync
    0.25
     owning
    0.24
    dont
    0.24
    Activations Density 14.037%

    No Known Activations