© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 8372
    Prev
    Next
    INDEX
    Explanations

    no or not

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĻ¤
    -0.33
    ä¸įè¶ħè¿ĩ
    -0.30
     além
    -0.28
    alan
    -0.28
    æĿ¥ä¸įåıĬ
    -0.27
    åıªæĥ³
    -0.27
    	except
    -0.27
    åıªåī©ä¸ĭ
    -0.27
    emet
    -0.26
    éĻ¤äºĨ
    -0.26
    POSITIVE LOGITS
    Increased
    0.27
     increased
    0.27
    å¢ŀå¤ļ
    0.26
    æĽ´å¤ļçļĦ
    0.26
     wider
    0.25
    æ¯Ķè¾ĥå¤ļ
    0.24
    ãģĮå¤ļãģĦ
    0.24
     Mil
    0.24
    åºŀ大
    0.24
     frequently
    0.24
    Activations Density 0.007%

    No Known Activations