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. 92933
    Prev
    Next
    INDEX
    Explanations

    scientific/medical texts

    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
     leaves
    -0.26
    roz
    -0.26
    éĺµå®¹
    -0.26
    leck
    -0.25
    apan
    -0.25
    ç͵
    -0.24
    cd
    -0.24
    æµį
    -0.24
    Leave
    -0.24
    ØŃÙĨ
    -0.24
    POSITIVE LOGITS
     PaÅĦst
    0.25
    ilst
    0.25
    强åζ
    0.25
    å¿ĥåĬ¨
    0.24
     loung
    0.24
    檩
    0.24
    uae
    0.24
    anyl
    0.24
    å¿Ĺ
    0.24
    ÅĽci
    0.24
    Activations Density 0.784%

    No Known Activations