© 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. 90048
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĬķ
    -0.28
    ienia
    -0.28
    çľ¼æ³ª
    -0.26
    нÑĥÑĤ
    -0.25
    IFS
    -0.25
    称
    -0.25
    ç»Łè®¡å±Ģ
    -0.24
    å±Ģ
    -0.24
    éĿ¢ç§¯
    -0.24
    кал
    -0.24
    POSITIVE LOGITS
    ynos
    0.27
    _chance
    0.26
    igram
    0.26
    .ll
    0.25
    agos
    0.25
    _CPP
    0.24
     generator
    0.23
    OMPI
    0.23
    RAP
    0.23
    _dicts
    0.23
    Activations Density 2.830%

    No Known Activations