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. 54570
    Prev
    Next
    INDEX
    Explanations

    copyright and legal 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
    çŃĭ
    -0.28
    æĪIJ绩åįķ
    -0.27
    åı·
    -0.27
    åĽŀåİ»
    -0.26
    带åĽŀ
    -0.25
    tics
    -0.25
    åĮħ容
    -0.25
    lename
    -0.24
     vent
    -0.24
     UIP
    -0.24
    POSITIVE LOGITS
     editors
    0.29
     lig
    0.27
     Lig
    0.26
    .setAuto
    0.26
     nextPage
    0.25
     colonies
    0.25
    å¹»
    0.25
    ungi
    0.24
    emi
    0.24
    anan
    0.24
    Activations Density 1.115%

    No Known Activations