© 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. 17819
    Prev
    Next
    INDEX
    Explanations

    9

    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
    URNS
    -0.30
    æł¡å¤ĸ
    -0.28
    .br
    -0.25
    UF
    -0.25
    .ordinal
    -0.25
    ug
    -0.25
     Mug
    -0.25
    istics
    -0.25
     gerne
    -0.24
    ÙĬض
    -0.24
    POSITIVE LOGITS
    ollo
    0.27
     pathname
    0.27
    REATE
    0.26
    -vers
    0.26
    建åħļ
    0.25
    çıŃåŃIJæĪIJåijĺ
    0.25
    emploi
    0.24
    ersh
    0.24
    ammers
    0.24
    alous
    0.24
    Activations Density 0.020%

    No Known Activations