© 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. 14-TRANSCODER-HP
    7. 39514
    Prev
    Next
    INDEX
    Explanations

    scientific papers and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Member
    -0.28
     Members
    -0.27
     MEMBER
    -0.26
    /member
    -0.26
     membership
    -0.26
     joined
    -0.26
    avs
    -0.26
    tems
    -0.26
     zug
    -0.26
     members
    -0.25
    POSITIVE LOGITS
    amation
    0.27
    enario
    0.26
    berman
    0.26
    aling
    0.25
    ppo
    0.25
    çł´
    0.25
    algorithm
    0.25
    eding
    0.25
    oppers
    0.24
    ograd
    0.24
    Activations Density 0.129%

    No Known Activations