© 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. 19-TRANSCODER-HP
    7. 4808
    Prev
    Next
    INDEX
    Explanations

    common short words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emic
    -0.30
    次è¦ģ
    -0.26
    emics
    -0.24
    ç½ijç«Ļé¦ĸ页
    -0.24
    em
    -0.24
    abad
    -0.24
    çļĦä¸Ģéĥ¨åĪĨ
    -0.24
    esa
    -0.24
    åĬ©çIJĨ
    -0.24
    icate
    -0.23
    POSITIVE LOGITS
     плаÑĤ
    0.27
     comm
    0.25
    _pe
    0.24
     conc
    0.24
     geb
    0.23
     Pra
    0.23
     disc
    0.23
     Twice
    0.23
     Plum
    0.22
    تبع
    0.22
    Activations Density 0.025%

    No Known Activations