© 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. 6030
    Prev
    Next
    INDEX
    Explanations

    Before, earlier, previous

    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
    bak
    -0.31
    ä¸įåħį
    -0.27
    æłĩçļĦ
    -0.25
    ãĤ¹ãĤ¿ãĥ³
    -0.25
    пеÑĩаÑĤ
    -0.24
    æŃ£å®Ĺ
    -0.24
    çĹ£
    -0.24
    财产
    -0.23
    ünde
    -0.23
    stood
    -0.23
    POSITIVE LOGITS
    æĢİä¹ĪåĬŀ
    0.26
    bower
    0.25
     border
    0.25
    æĹłè®ºæĺ¯
    0.25
    åľ°ä¸Ĭ
    0.25
     darauf
    0.25
    该æĢİä¹ĪåĬŀ
    0.25
     Berk
    0.24
    ÑĮÑİ
    0.24
    ç°ĩ
    0.24
    Activations Density 0.035%

    No Known Activations