© 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. 6395
    Prev
    Next
    INDEX
    Explanations

    Question answering

    np_max-act · gemini-2.0-flash
    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
    ä¼´
    -0.30
    æ°´éĿ¢
    -0.27
    лей
    -0.26
    aille
    -0.26
     ton
    -0.25
    amate
    -0.24
    ì¹ĺ
    -0.24
    ç¦ħ
    -0.24
    ku
    -0.24
    ä¸Ģè§Ĵ
    -0.24
    POSITIVE LOGITS
    iculty
    0.28
    (language
    0.26
     eg
    0.26
    otyping
    0.25
    ä¾Ľæ±Ĥ
    0.24
    __.__
    0.24
    __↵↵
    0.23
    éĻIJé¢Ŀ
    0.23
    åĬ³åĬ¨
    0.23
    ัว
    0.23
    Activations Density 0.006%

    No Known Activations