© 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. 5163
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    åħ¬åı¸å°Ĩ
    -0.28
    éĺ¡
    -0.27
    ç½ij讯
    -0.27
     dop
    -0.25
    ÊĬ
    -0.24
    ÄĻd
    -0.24
    ">(
    -0.24
     burnt
    -0.23
    isme
    -0.23
    èıħ
    -0.23
    POSITIVE LOGITS
    achu
    0.28
    Convention
    0.27
    ÑĦин
    0.27
    ADVERTISEMENT
    0.26
    æݾ
    0.25
    ilder
    0.25
    ga
    0.25
    åı¯è¾¾
    0.25
     Andrews
    0.24
    file
    0.24
    Activations Density 0.189%

    No Known Activations