© 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. 88102
    Prev
    Next
    INDEX
    Explanations

    War and military conflicts

    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
     remaining
    -0.31
    Mon
    -0.28
    åī©ä½Ļ
    -0.27
    _remaining
    -0.27
    remaining
    -0.26
    éĹŃ
    -0.26
    _mon
    -0.26
     singly
    -0.26
    quer
    -0.25
    Remaining
    -0.25
    POSITIVE LOGITS
    âľķ
    0.26
    lifetime
    0.25
     tượng
    0.24
    itch
    0.24
    critical
    0.24
    é£İ鼨
    0.23
    uids
    0.23
    feld
    0.23
    CHAIN
    0.23
    åijĬè¯īä½ł
    0.23
    Activations Density 14.619%

    No Known Activations