© 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. 18-TRANSCODER-HP
    7. 88452
    Prev
    Next
    INDEX
    Explanations

    Navy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÂŃ
    -0.26
    å¤ĩ
    -0.26
     docking
    -0.26
     Domino
    -0.26
    éģ¿
    -0.25
    åģļ强
    -0.24
    gL
    -0.24
     Array
    -0.23
    omer
    -0.23
    ouble
    -0.23
    POSITIVE LOGITS
    人çī©
    0.27
    ÑĮÑıн
    0.25
    åħ¹
    0.25
    æĽ´å¤ļ精彩
    0.24
    nze
    0.24
    WSC
    0.24
    +":
    0.24
     interactions
    0.24
    å·¥ä½ľèĢħ
    0.24
     observations
    0.23
    Activations Density 11.893%

    No Known Activations