© 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. 18-TRANSCODER-HP
    7. 90164
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Pull
    -0.24
    owell
    -0.23
     ||=
    -0.23
    æĪIJç«ĭ
    -0.23
    onDelete
    -0.23
    ,{"
    -0.23
     der
    -0.22
    /XMLSchema
    -0.22
    ull
    -0.22
    .removeAll
    -0.22
    POSITIVE LOGITS
    èĪ¸
    0.26
    Edition
    0.24
     RECT
    0.24
     Magn
    0.24
    ãĤ·ãĥ§ãĥ¼
    0.23
    iors
    0.23
     ÐĵоÑĢ
    0.23
     brush
    0.23
    inceton
    0.22
    دÙĪÙĨ
    0.22
    Activations Density 82.852%

    No Known Activations