© 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. 25-TRANSCODER-HP
    7. 109406
    Prev
    Next
    INDEX
    Explanations

    scaling

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    enk
    -0.32
    åıĺå¼Ĥ
    -0.27
    otics
    -0.27
    宽æĿ¾
    -0.26
    arial
    -0.26
    Markers
    -0.26
     Katz
    -0.25
    erb
    -0.25
    iber
    -0.25
     Ladies
    -0.25
    POSITIVE LOGITS
     both
    0.28
     quant
    0.28
     trusted
    0.28
     system
    0.27
     filesystem
    0.27
     pai
    0.25
    TO
    0.25
    cp
    0.25
     users
    0.24
    filesystem
    0.24
    Activations Density 1.002%

    No Known Activations