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. 1700
    Prev
    Next
    INDEX
    Explanations

    Medical terms

    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
    èµ¶
    -0.28
    æĸ¹åIJij
    -0.27
    RAR
    -0.26
     destin
    -0.26
     teams
    -0.26
    ĥģ
    -0.26
    nar
    -0.25
    ä¸ĬçļĦ
    -0.25
    鬣
    -0.24
    è°Ī
    -0.24
    POSITIVE LOGITS
    ä¾Ĺ
    0.27
     Dungeons
    0.26
    éĢļ车
    0.26
     Glock
    0.26
     desn
    0.25
    Perfect
    0.24
    yre
    0.24
    ÑĪек
    0.24
    ä½Ĩä¸įéĻIJäºİ
    0.24
     erot
    0.24
    Activations Density 0.004%

    No Known Activations