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. 123
    Prev
    Next
    INDEX
    Explanations

    elementary school

    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
     PLUGIN
    -0.27
    çļĦçĶ»éĿ¢
    -0.26
    ény
    -0.26
    æİ´
    -0.26
     jealousy
    -0.25
    estroy
    -0.25
    é¡ĺ
    -0.25
    æĮ¯ãĤĬ
    -0.25
     väl
    -0.25
    'E
    -0.25
    POSITIVE LOGITS
     CG
    0.28
     hab
    0.27
    ç³»
    0.26
    #
    0.26
    ral
    0.26
    (#
    0.25
    #,
    0.25
     Nam
    0.24
    俯
    0.24
    iterate
    0.24
    Activations Density 0.001%

    No Known Activations