© 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. 90012
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    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
    åķľ
    -0.29
    wyn
    -0.27
    _seconds
    -0.26
    edImage
    -0.26
    hooks
    -0.25
    _framework
    -0.25
    writeln
    -0.25
    PickerController
    -0.25
    erne
    -0.25
    eshire
    -0.25
    POSITIVE LOGITS
    ther
    0.29
    åŁ¹åħ»
    0.27
    ument
    0.27
    R
    0.26
     density
    0.25
    uth
    0.25
     pand
    0.24
     sorte
    0.24
    Density
    0.24
     parentId
    0.24
    Activations Density 17.088%

    No Known Activations