© 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. 6495
    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
    空
    -0.26
    空çĻ½
    -0.26
    代
    -0.26
    建ç«ĭäºĨ
    -0.25
    åįĬ
    -0.25
    ä¸ĭä¸Ģ代
    -0.25
    éĹ´éļĶ
    -0.25
    åIJ«ä¹ī
    -0.24
    æĽ´å¿«
    -0.24
    oque
    -0.24
    POSITIVE LOGITS
    被æīĵ
    0.31
     Loren
    0.25
     boil
    0.24
    èİĴ
    0.24
     anatom
    0.24
    Incoming
    0.24
    æĺ¯ä¸ŃåĽ½
    0.24
    endale
    0.23
    饽
    0.23
    å®īåħ¨ä¿Ŀéļľ
    0.23
    Activations Density 0.047%

    No Known Activations

    This feature has no known activations.