© 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. 23-TRANSCODER-HP
    7. 162943
    Prev
    Next
    INDEX
    Explanations

    Legal disclaimers/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nor
    -1.23
     anymore
    -0.98
    nor
    -0.89
    ä¹Łæ²¡æľī
    -0.82
    èĢĮæĺ¯
    -0.82
    ä¹Łä¸į
    -0.79
    Nor
    -0.79
     Nor
    -0.78
    ä¹Łæ²¡
    -0.67
    ä¹Łä¸įä¼ļ
    -0.66
    POSITIVE LOGITS
     both
    0.35
    both
    0.34
    èĢĮä¸įæĺ¯
    0.32
    èĢĮéĿŀ
    0.31
    Both
    0.31
     Both
    0.29
    æīįèĥ½å¤Ł
    0.28
    åIJĮæĹ¶ä¹Łæĺ¯
    0.28
     almost
    0.27
     både
    0.26
    Activations Density 0.009%

    No Known Activations