© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 88735
    Prev
    Next
    INDEX
    Explanations

    Text fragments/abbreviations

    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
    AAA
    -0.27
    otte
    -0.25
    妻
    -0.25
    çĭ¸
    -0.25
     borderline
    -0.25
    ("");č↵
    -0.25
    Streamer
    -0.24
    اÙĪ
    -0.24
    寡
    -0.24
    ("");
    -0.23
    POSITIVE LOGITS
    scious
    0.29
     experiment
    0.29
    pread
    0.27
    è§Ĥæij©
    0.26
    ROME
    0.25
    ständ
    0.24
     Stores
    0.24
     impro
    0.24
     crud
    0.24
    gages
    0.24
    Activations Density 1.070%

    No Known Activations