© 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. 5198
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ogs
    -0.26
    èķ¨
    -0.25
     terminate
    -0.25
    (TreeNode
    -0.24
    ÑīиÑĤ
    -0.24
     Step
    -0.23
    ombs
    -0.23
    oen
    -0.23
     hã
    -0.23
     burnt
    -0.23
    POSITIVE LOGITS
    éŃĤ
    0.28
    ä¸ľè¥¿
    0.26
    nea
    0.24
    éĵ¾æİ¥
    0.24
    è§Ħå®ļ
    0.24
     est
    0.23
    æ´¾
    0.23
     chinese
    0.23
    WF
    0.23
    æ¼ĶåĮĸ
    0.23
    Activations Density 0.155%

    No Known Activations

    This feature has no known activations.