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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5790
    Prev
    Next
    INDEX
    Explanations

    code/programming

    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
     owned
    -0.28
     Bridges
    -0.27
    oter
    -0.27
    rought
    -0.26
    und
    -0.25
    er
    -0.25
    pci
    -0.25
    çļĦå·¥ä½ľ
    -0.25
    æ··åĩĿ
    -0.24
    stairs
    -0.24
    POSITIVE LOGITS
    Defs
    0.29
    积æŀģåıĤä¸İ
    0.29
    heed
    0.26
     —↵↵
    0.26
    minent
    0.25
    Serialization
    0.24
    kul
    0.24
    é¢Ĺ
    0.24
    积æŀģ
    0.24
     gep
    0.23
    Activations Density 0.007%

    No Known Activations