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. 98081
    Prev
    Next
    INDEX
    Explanations

    scientific research papers

    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
    aris
    -0.27
     IMO
    -0.26
     vo
    -0.25
    aru
    -0.25
     actual
    -0.24
     actually
    -0.24
    å®ŀéĻħä¸Ĭ
    -0.24
    Pe
    -0.24
     surface
    -0.23
    z
    -0.23
    POSITIVE LOGITS
    椽
    0.29
    ä»ĸ们æĺ¯
    0.26
    orp
    0.26
    篮
    0.25
     siti
    0.24
    idge
    0.24
    ä¹°ä¸ľè¥¿
    0.24
     itemView
    0.23
    nelly
    0.23
    åģľä¸ĭ
    0.23
    Activations Density 0.003%

    No Known Activations