© 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. 9-TRANSCODER-HP
    7. 30476
    Prev
    Next
    INDEX
    Explanations

    Technical, research text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    brain
    -0.38
     brains
    -0.36
     brain
    -0.35
    èĦij
    -0.35
    大èĦij
    -0.33
    brains
    -0.30
    umbo
    -0.29
    Brain
    -0.28
     minds
    -0.28
     Brain
    -0.28
    POSITIVE LOGITS
     retal
    0.28
    æĶĴ
    0.27
    Dear
    0.27
    òa
    0.26
    央
    0.25
    ç¾İ好çĶŁæ´»
    0.24
    ORED
    0.24
    æݥ轨
    0.24
    ORTH
    0.24
     closest
    0.24
    Activations Density 5.132%

    No Known Activations