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. 46706
    Prev
    Next
    INDEX
    Explanations

    code or text

    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
    trail
    -0.28
    èݲ
    -0.28
     ngược
    -0.27
    请èģĶç³»
    -0.26
     TLabel
    -0.26
     trail
    -0.26
    irie
    -0.25
    userinfo
    -0.24
     liner
    -0.24
    ä¼¼çļĦ
    -0.23
    POSITIVE LOGITS
     Casting
    0.25
    ination
    0.24
    otor
    0.24
     brig
    0.23
    keys
    0.23
    mium
    0.23
    INATION
    0.23
     kurz
    0.23
    AYER
    0.23
    æ´ĭèij±
    0.23
    Activations Density 0.001%

    No Known Activations