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. 11-TRANSCODER-HP
    4. 46393
    Prev
    Next
    INDEX
    Explanations

    code, databases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çī©
    -0.27
    ä¹ĭäºī
    -0.26
    笼
    -0.25
    ÃĹ↵↵
    -0.25
    (LOG
    -0.24
    å±ī
    -0.24
    åĽ½äº§
    -0.24
    (fh
    -0.24
    etrics
    -0.24
    iker
    -0.23
    POSITIVE LOGITS
    æĻļä¼ļ
    0.28
    ipur
    0.27
     spatial
    0.26
    รà¸Ńย
    0.26
    çīĮ
    0.26
     spins
    0.25
    sla
    0.25
     facts
    0.24
    actical
    0.24
    ÅĽl
    0.23
    Activations Density 0.039%

    No Known Activations