© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 290
    Prev
    Next
    INDEX
    Explanations

    articles/possessive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ§Ľ
    -0.33
    odes
    -0.26
    attered
    -0.25
    åĪģ
    -0.24
    è¯Į
    -0.24
    odic
    -0.23
    ãģĭãģĦ
    -0.23
    æľīä¸Ģå®ļ
    -0.23
    ció
    -0.23
    .serializer
    -0.23
    POSITIVE LOGITS
     rendering
    0.26
    éħįæĸ¹
    0.25
    èļĮ
    0.25
    æĺ¯å¦Ĥä½ķ
    0.25
    /fast
    0.24
    çĶŁåij½çļĦ
    0.24
     TableColumn
    0.24
     Parm
    0.24
     dru
    0.24
    _AF
    0.24
    Activations Density 1.635%

    No Known Activations