© 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. 88208
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and geometry

    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
    è¸Ĭ
    -0.27
    ctest
    -0.26
    afety
    -0.26
    éĩı产
    -0.25
    éĺ²æ±Ľ
    -0.25
    Safety
    -0.25
    мед
    -0.25
    oning
    -0.24
    Defaults
    -0.24
    -fw
    -0.24
    POSITIVE LOGITS
     hyper
    0.28
    hyper
    0.28
    izoph
    0.27
    åı£è¢ĭ
    0.26
     cz
    0.25
    æĴķ
    0.24
    Hyper
    0.24
    çŃĸ
    0.24
     |↵
    0.24
    >"+↵
    0.24
    Activations Density 12.776%

    No Known Activations