© 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. 7858
    Prev
    Next
    INDEX
    Explanations

    Names of people

    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
    rod
    -0.31
    ry
    -0.29
     refin
    -0.26
     arc
    -0.26
    è¿ĺä¸įæĺ¯
    -0.25
     generally
    -0.25
    маÑĢ
    -0.24
     substitute
    -0.24
    simple
    -0.24
    early
    -0.24
    POSITIVE LOGITS
    çī¹æĸ¯
    0.26
    addtogroup
    0.25
     dumpster
    0.24
    zung
    0.24
    asthan
    0.24
    åįħ
    0.23
    abble
    0.23
     OMIT
    0.23
    ctest
    0.23
    trak
    0.23
    Activations Density 0.014%

    No Known Activations