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. 47254
    Prev
    Next
    INDEX
    Explanations

    documents

    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
    笺
    -0.27
    騰
    -0.25
    èħ¾
    -0.25
    å̾åIJij
    -0.25
    lington
    -0.24
    äºĴéĢļ
    -0.24
    _bo
    -0.24
    ç¦ıåĪ©
    -0.24
    纸ä¸Ĭ
    -0.24
    äºŃ
    -0.24
    POSITIVE LOGITS
    é¢Ľ
    0.27
    DataAdapter
    0.27
    osg
    0.26
     pov
    0.25
    %%%%%%%%%%%%%%%%
    0.24
    ciÄħ
    0.24
     Cand
    0.24
    orama
    0.24
    stdin
    0.23
    人寿
    0.23
    Activations Density 0.093%

    No Known Activations