© 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. 5413
    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
     pee
    -0.25
    ichen
    -0.25
    èĢģ人家
    -0.24
    ëĭIJ
    -0.24
     told
    -0.23
    _LESS
    -0.23
    eson
    -0.23
     Markup
    -0.23
    expect
    -0.23
    Less
    -0.23
    POSITIVE LOGITS
    æµĩ
    0.26
    ä¼Ļ
    0.25
     wig
    0.24
    æĶ¹åĪ¶
    0.24
    éĹ¨æ§Ľ
    0.24
    严
    0.24
    >{!!
    0.24
    ä½ĵåĨħ
    0.24
     getType
    0.24
    æľī害
    0.24
    Activations Density 0.163%

    No Known Activations

    This feature has no known activations.