© 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. 17960
    Prev
    Next
    INDEX
    Explanations

    re

    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
     succ
    -0.28
    .Bounds
    -0.28
     pe
    -0.28
    è¦ĨçĽĸ
    -0.27
    ests
    -0.27
    succ
    -0.26
    asc
    -0.26
    res
    -0.26
    utherford
    -0.26
     dc
    -0.25
    POSITIVE LOGITS
    ismatic
    0.30
     imagined
    0.30
    ilder
    0.27
    åį°è±¡
    0.26
    uario
    0.26
    åįģä½³
    0.26
     Imag
    0.26
     pictured
    0.25
    phant
    0.24
    baum
    0.24
    Activations Density 0.920%

    No Known Activations