© 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. 19960
    Prev
    Next
    INDEX
    Explanations

    the, following

    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
     alike
    -0.30
    ector
    -0.27
    imet
    -0.26
    ARI
    -0.26
    prs
    -0.25
    å¸ĪèĮĥ
    -0.25
    ТÐIJ
    -0.25
    ument
    -0.25
    LEY
    -0.25
    pir
    -0.24
    POSITIVE LOGITS
    tracks
    0.30
    bang
    0.27
     tract
    0.26
    osh
    0.26
    ocks
    0.25
     autob
    0.24
    StackSize
    0.24
    驱åĬ¨
    0.24
    åłĨ
    0.24
    驳
    0.24
    Activations Density 0.046%

    No Known Activations