© 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. 40853
    Prev
    Next
    INDEX
    Explanations

    up

    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
    ajes
    -0.27
    çļĦ人éĥ½
    -0.26
    geries
    -0.26
    restriction
    -0.26
    Born
    -0.26
    å°ıé¾Ļ
    -0.25
    次ä¼ļè®®
    -0.25
    tors
    -0.25
    udu
    -0.24
    bol
    -0.24
    POSITIVE LOGITS
     most
    0.35
     flooded
    0.31
     torn
    0.31
     prior
    0.29
     haunted
    0.28
     raised
    0.28
    ared
    0.27
     poor
    0.27
     working
    0.27
     playing
    0.27
    Activations Density 0.010%

    No Known Activations