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. 1475
    Prev
    Next
    INDEX
    Explanations

    Chemical compounds/research

    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
    åħ¥åı£
    -0.26
    æľ«
    -0.26
    ETO
    -0.25
    主ä¹īæĢĿæĥ³
    -0.25
    rances
    -0.24
    .ssl
    -0.24
    åĽ¾ä¹¦
    -0.24
     #@
    -0.24
    book
    -0.24
    å·®åĪ«
    -0.24
    POSITIVE LOGITS
    irth
    0.28
    (mut
    0.28
     cuck
    0.27
       
    0.27
     kitchens
    0.26
    ÑĢом
    0.26
    erness
    0.26
    mas
    0.25
    rees
    0.25
    itta
    0.24
    Activations Density 0.003%

    No Known Activations