© 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. 31-TRANSCODER-HP
    7. 19063
    Prev
    Next
    INDEX
    Explanations

    Japanese text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UGHT
    -0.30
    æ¸ħ
    -0.27
    èIJĮ
    -0.27
    åĪĹ
    -0.25
     Ars
    -0.24
     winding
    -0.24
     repr
    -0.23
    à¤
    -0.23
    ائ
    -0.23
    ]<<
    -0.23
    POSITIVE LOGITS
    æĹ¥æľ¬äºº
    0.32
    çļĦæĹ¥
    0.31
     Japanese
    0.30
    åľ¨æĹ¥æľ¬
    0.30
     Japan
    0.30
    éªħ
    0.29
    æĹ¥æĬ¥
    0.28
    æĹ¥æľ¬
    0.27
    æĹ¥
    0.27
    è¡ĮæĶ¿éĥ¨éŨ
    0.26
    Activations Density 0.903%

    No Known Activations