© 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. 5431
    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
    ç©¿
    -0.32
    zar
    -0.31
    çĻ¾åĪĨ
    -0.29
    çļĦæ¯Ķä¾ĭ
    -0.27
    é¼»
    -0.27
    æŀģ
    -0.27
    æ¯Ķä¾ĭ
    -0.27
    ãģªãģĮãĤī
    -0.26
    éĥ¨éķ¿
    -0.26
    åħ³èģĶ
    -0.25
    POSITIVE LOGITS
    æŃ£åĵģ
    0.25
    omet
    0.25
    quete
    0.25
    è·Łå¥¹
    0.25
    ackers
    0.25
     qualifiers
    0.25
     withStyles
    0.25
    å°±å¤ŁäºĨ
    0.24
    ï¼ģ↵↵↵↵
    0.24
    é«ĺçŃīéĻ¢æł¡
    0.24
    Activations Density 0.675%

    No Known Activations

    This feature has no known activations.