© 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. 14-TRANSCODER-HP
    7. 41602
    Prev
    Next
    INDEX
    Explanations

    Ar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     POSIX
    -0.27
     пÑĢодолжа
    -0.27
     toe
    -0.26
     sheets
    -0.26
     Suit
    -0.26
     proprietor
    -0.26
    交代
    -0.25
     Câm
    -0.25
     lin
    -0.24
     soup
    -0.24
    POSITIVE LOGITS
    æij©
    0.29
    Mo
    0.28
    uture
    0.28
    æij©æīĺ
    0.26
    åĪºæ¿Ģ
    0.26
    жив
    0.26
    ÑıÑĤи
    0.26
    çĶ¨å¿ĥ
    0.25
    æĸ©
    0.25
     advanced
    0.25
    Activations Density 0.063%

    No Known Activations