© 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. 27-TRANSCODER-HP
    7. 9843
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    aci
    -0.27
    åģļ人
    -0.26
    irk
    -0.26
    ellen
    -0.25
    åѦ
    -0.25
    iger
    -0.25
    ix
    -0.25
    åľŁè±Ĩ
    -0.25
    ac
    -0.25
    æľĢåıĹ
    -0.25
    POSITIVE LOGITS
    phia
    0.30
    è¯ģåĪ¸æĬķèµĦ
    0.27
    å®īåħ¨ä¿Ŀéļľ
    0.25
    念头
    0.25
     catching
    0.25
    æĪĽ
    0.25
    转åıij
    0.24
    .parameters
    0.24
    ÅĪ
    0.24
    variables
    0.23
    Activations Density 0.000%

    No Known Activations