© 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. 32-TRANSCODER-HP
    7. 40828
    Prev
    Next
    INDEX
    Explanations

    government acts/bills

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    agrid
    -0.30
     legitimacy
    -0.28
    uli
    -0.27
    imity
    -0.26
    heimer
    -0.26
    irement
    -0.25
    模仿
    -0.25
    arily
    -0.24
    athi
    -0.24
    [href
    -0.24
    POSITIVE LOGITS
     US
    0.27
    avo
    0.27
     Replies
    0.27
    åİĭ
    0.26
    rooms
    0.25
    ilde
    0.25
     Revel
    0.25
    READ
    0.25
     "==
    0.25
    elt
    0.25
    Activations Density 0.004%

    No Known Activations