© 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. 31-TRANSCODER-HP
    7. 17887
    Prev
    Next
    INDEX
    Explanations

    proper names and computer language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ÑĤÑĥÑĢ
    -0.31
    ARI
    -0.31
    evin
    -0.29
     Territories
    -0.29
    ari
    -0.28
    tur
    -0.27
    SUPER
    -0.26
    zig
    -0.26
    æ¸ħæĸ°
    -0.26
    SUB
    -0.25
    POSITIVE LOGITS
    anes
    0.28
    ocate
    0.28
     olan
    0.26
    ados
    0.25
     career
    0.25
     Merc
    0.25
    ibo
    0.25
    aines
    0.25
    emplo
    0.24
    åģļä»Ģä¹Ī
    0.24
    Activations Density 0.239%

    No Known Activations