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. 98007
    Prev
    Next
    INDEX
    Explanations

    Herald

    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
    å¾ĭ
    -0.34
    apg
    -0.27
    å½±éŁ³
    -0.24
     Roku
    -0.24
    uste
    -0.24
    å°ĺ
    -0.24
    æ³»
    -0.24
     Vect
    -0.24
     Dust
    -0.23
     penny
    -0.23
    POSITIVE LOGITS
    æIJħæĭĮ
    0.30
    æ©Ħæ¦Ħ
    0.27
    è¾ŀ
    0.26
    ouri
    0.26
    imos
    0.25
    à¹Īม
    0.25
    bag
    0.25
    ITO
    0.24
    ä»įå°Ĩ
    0.24
    altar
    0.24
    Activations Density 0.002%

    No Known Activations