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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5005
    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
    iare
    -0.26
    sr
    -0.25
     overall
    -0.25
    aad
    -0.25
    urve
    -0.25
    åĵij
    -0.24
    ioned
    -0.24
    åľ¨èģĮ
    -0.24
    shire
    -0.24
    indexed
    -0.24
    POSITIVE LOGITS
    -collapse
    0.26
    ä¹ŁéĿŀ常
    0.25
    phasis
    0.25
    æĬĬå®ĥ
    0.24
     correlate
    0.24
    Ø´Ùħ
    0.24
    ä¸ĩåı°
    0.23
    _rm
    0.23
    CJK
    0.23
     ÑģовеÑĢÑĪен
    0.23
    Activations Density 0.025%

    No Known Activations

    This feature has no known activations.