© 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. 4857
    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
    æ³¢
    -0.28
     wave
    -0.26
    bour
    -0.26
    è°
    -0.24
    çĸı
    -0.24
    笼
    -0.24
    è¡Įãģ£ãģ¦
    -0.24
    /wiki
    -0.24
    æijĺ
    -0.23
    abela
    -0.23
    POSITIVE LOGITS
    thritis
    0.28
    å¾Ĺå¾Ī好
    0.28
    Comparer
    0.26
    åľ¨å¤ĸéĿ¢
    0.25
     darn
    0.25
    mega
    0.24
     whoever
    0.24
    çīĪæĿĥæīĢæľī
    0.24
    åı£
    0.24
    OrFail
    0.24
    Activations Density 1.412%

    No Known Activations

    This feature has no known activations.