© 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. 35-TRANSCODER-HP
    7. 40621
    Prev
    Next
    INDEX
    Explanations

    Code and programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    rops
    -0.32
    iest
    -0.31
    rep
    -0.27
    lush
    -0.26
     reveal
    -0.26
    ç²Ĺç³Ļ
    -0.26
     reveals
    -0.26
     flashes
    -0.25
    lash
    -0.25
    lias
    -0.25
    POSITIVE LOGITS
    mland
    0.27
    yne
    0.27
    udp
    0.26
    wnd
    0.25
    bre
    0.25
     federation
    0.24
    >ID
    0.23
    builder
    0.23
    Congratulations
    0.23
     IDD
    0.23
    Activations Density 0.040%

    No Known Activations