© 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. 14-TRANSCODER-HP
    7. 39533
    Prev
    Next
    INDEX
    Explanations

    since

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    èĢĮå·²
    -0.30
    æīĵåĮħ
    -0.26
     $($
    -0.25
    elic
    -0.25
    ↵                    ↵
    -0.25
    orns
    -0.24
    å¾·æĭī
    -0.24
    éĤ£ä¹Īå¤ļ
    -0.23
     broader
    -0.23
    FN
    -0.23
    POSITIVE LOGITS
    æľĿçĿĢ
    0.27
    æĦ¿æľĽ
    0.26
    acular
    0.24
    inputEmail
    0.24
    Computed
    0.24
     Wat
    0.24
    acent
    0.24
    æģķ
    0.23
     photoc
    0.23
    licence
    0.23
    Activations Density 1.002%

    No Known Activations