© 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. 90124
    Prev
    Next
    INDEX
    Explanations

    mathematics

    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
     resolution
    -0.26
    éĢı
    -0.25
     overwhelmingly
    -0.25
    央
    -0.24
    æĹģ
    -0.24
    çĹĽ
    -0.24
    å®Ľ
    -0.24
    è¡Ķæİ¥
    -0.24
    票
    -0.24
    ewe
    -0.23
    POSITIVE LOGITS
    yne
    0.28
    cord
    0.28
    å½±åĵįåĬĽçļĦ
    0.28
    ãģ°ãģĭãĤĬ
    0.28
     Thumb
    0.26
     Armen
    0.25
     Guests
    0.25
    ecc
    0.25
    vertical
    0.24
    criptors
    0.24
    Activations Density 9.074%

    No Known Activations