© 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. 9641
    Prev
    Next
    INDEX
    Explanations

    data

    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
    ndon
    -0.28
    iams
    -0.27
    ["@
    -0.26
     __________________↵↵
    -0.25
    ï¿£
    -0.25
    printing
    -0.25
     anecdotes
    -0.24
    ucker
    -0.24
    ainties
    -0.24
    -print
    -0.24
    POSITIVE LOGITS
     data
    0.45
    Content
    0.39
     content
    0.38
    æķ°æį®
    0.37
     Content
    0.32
    Data
    0.32
    data
    0.32
    _content
    0.32
    åĨħ容
    0.31
     bytes
    0.31
    Activations Density 0.024%

    No Known Activations