© 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. 41783
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    ä¸ī项
    -0.31
    ä»Ģä¹Īåij¢
    -0.27
    çĬĬ
    -0.27
    ignet
    -0.26
    erne
    -0.26
     Ned
    -0.25
    åĨ³
    -0.25
     Annex
    -0.25
    çªį
    -0.24
     etc
    -0.24
    POSITIVE LOGITS
     Crate
    0.28
    antha
    0.26
    æ¦
    0.25
    俪
    0.25
     spirits
    0.24
    Translator
    0.24
     dra
    0.24
     DETAILS
    0.24
    对ç«ĭ
    0.24
    nts
    0.24
    Activations Density 1.986%

    No Known Activations