© 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. 5238
    Prev
    Next
    INDEX
    Explanations

    scientific research papers

    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
    åĤ¢
    -0.28
    odom
    -0.28
     assum
    -0.26
    orch
    -0.25
    swire
    -0.25
    agento
    -0.24
    ******↵
    -0.24
    ool
    -0.24
     versus
    -0.24
    ishop
    -0.24
    POSITIVE LOGITS
    adera
    0.28
    lotte
    0.27
    bane
    0.25
    cec
    0.25
    æĬķèµĦ人
    0.25
    zens
    0.25
    ãĤĭãĤĪãģĨãģ«
    0.25
    steller
    0.24
    zan
    0.24
    >+
    0.24
    Activations Density 0.041%

    No Known Activations