© 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. 5381
    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
    ogan
    -0.31
    æĪĸå¤ļ
    -0.28
    ogen
    -0.27
    æľįåĬ¡åĮº
    -0.26
    itary
    -0.26
    -separated
    -0.24
    KN
    -0.24
    Occurs
    -0.23
     prevail
    -0.23
    ä½ľé£İ
    -0.23
    POSITIVE LOGITS
    马åĬĽ
    0.26
    æ¶ħ
    0.25
    åĴĮå°ļ
    0.25
    оÑī
    0.24
    à¹Ģà¸Ł
    0.24
    XY
    0.23
    æĸĩçĮ®
    0.23
     Sandbox
    0.23
    Max
    0.23
    ZX
    0.23
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.