Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 7-TRANSCODER-HP
    4. 1689
    Prev
    Next
    INDEX
    Explanations

    ology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .insertBefore
    -0.31
    è¿ŀäºij
    -0.27
    åŁİ乡å±ħæ°ij
    -0.26
     lá»Ļ
    -0.26
    culo
    -0.26
    езн
    -0.26
    лÑĮн
    -0.25
    ibel
    -0.25
    iola
    -0.24
    isans
    -0.24
    POSITIVE LOGITS
    bum
    0.25
    /topics
    0.24
    imports
    0.24
     licked
    0.23
     benchmarks
    0.23
     bios
    0.23
    èijĹ
    0.23
    ìϏ
    0.23
    filled
    0.22
     breaks
    0.22
    Activations Density 0.001%

    No Known Activations