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. 53880
    Prev
    Next
    INDEX
    Explanations

    one

    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
    æį»
    -0.28
    çıŃ
    -0.26
    Deck
    -0.25
    è¸ıå®ŀ
    -0.25
    зам
    -0.25
    å°±è¿ij
    -0.25
     loose
    -0.24
    åıĪ好
    -0.24
    heim
    -0.24
    å³ģ
    -0.24
    POSITIVE LOGITS
    æĦŁ
    0.28
    æĦŁå®ĺ
    0.28
    òng
    0.27
    åħ´
    0.26
    uples
    0.26
    被æī§è¡Į
    0.25
    ç²¾
    0.25
     RIGHTS
    0.24
    _PLUGIN
    0.24
    angible
    0.24
    Activations Density 0.051%

    No Known Activations