© 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. 4817
    Prev
    Next
    INDEX
    Explanations

    scientific/technical descriptions

    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
    æ¯Ķè¾ĥ
    -0.27
     totaling
    -0.27
    æĺ¯åIJ¦ä¼ļ
    -0.26
    æĮĤ
    -0.25
    endid
    -0.25
     cÄĥng
    -0.24
    priority
    -0.24
    è¾ĥ
    -0.24
    大å¹ħ
    -0.24
    æĤ«
    -0.24
    POSITIVE LOGITS
    ARRIER
    0.27
    anje
    0.27
    arbon
    0.26
    QP
    0.26
     edible
    0.25
     antid
    0.25
    æĹłåģ¿
    0.25
    èµĦæºIJåħ±äº«
    0.25
    gy
    0.24
    fromJson
    0.24
    Activations Density 0.039%

    No Known Activations