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. 46434
    Prev
    Next
    INDEX
    Explanations

    measurements

    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
    .dimensions
    -0.28
    thalm
    -0.27
    å®ī康
    -0.27
    æĤĮ
    -0.25
    票
    -0.25
    éĽĨèģļ
    -0.25
    	inst
    -0.24
    çļĦæķ°éĩı
    -0.24
    .rm
    -0.24
    bill
    -0.24
    POSITIVE LOGITS
     pragma
    0.29
    ever
    0.29
    æıIJåĩºçļĦ
    0.29
     mim
    0.28
     male
    0.27
    è°ħ
    0.27
     gest
    0.26
     bisher
    0.26
     muc
    0.26
    ä¸į容æĺĵ
    0.26
    Activations Density 0.013%

    No Known Activations