© 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. 31-TRANSCODER-HP
    7. 19816
    Prev
    Next
    INDEX
    Explanations

    transfer between genomes/routes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    standing
    -0.31
    Ñĭваем
    -0.28
    å²Ĺä½į
    -0.27
    athon
    -0.27
    _jobs
    -0.25
    kins
    -0.25
    çĶŁäº§åİĤ家
    -0.25
    uates
    -0.25
    åľ¨çĶŁæ´»ä¸Ń
    -0.25
     Mont
    -0.24
    POSITIVE LOGITS
    综åIJĪ
    0.29
    æĥħ
    0.28
    è¡°
    0.27
    åģı离
    0.27
    çļĦ人
    0.27
    afari
    0.26
     occult
    0.26
     synthesis
    0.26
    Routes
    0.25
    syn
    0.25
    Activations Density 1.198%

    No Known Activations