© 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. 33-TRANSCODER-HP
    7. 54701
    Prev
    Next
    INDEX
    Explanations

    sports team owners/bosses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     reversible
    -0.27
    dyn
    -0.27
    chas
    -0.26
     Struct
    -0.26
    Coordinator
    -0.25
     Lid
    -0.25
    ä¾Ŀèµĸ
    -0.25
     Shack
    -0.24
    herits
    -0.24
    ensible
    -0.23
    POSITIVE LOGITS
    adia
    0.28
    soles
    0.27
    osing
    0.27
    éĺŁåijĺ
    0.27
    ig
    0.27
    æ´¾
    0.26
    èĩ£
    0.26
    adians
    0.25
    iscal
    0.24
    åºŀ
    0.24
    Activations Density 0.046%

    No Known Activations