© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 39803
    Prev
    Next
    INDEX
    Explanations

    what

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å»ĵ
    -0.28
    éľģ
    -0.26
    affer
    -0.25
    iker
    -0.25
    使èĢħ
    -0.25
     Reconstruction
    -0.24
    оÑģÑĤей
    -0.24
     META
    -0.24
    cor
    -0.24
    ä¸Ģ举
    -0.24
    POSITIVE LOGITS
    æľīæĿ¡ä»¶
    0.33
    arium
    0.29
    asma
    0.26
    æľīæĿ¡ä»¶çļĦ
    0.26
    æľīéĴĪ对æĢ§
    0.26
    encies
    0.26
    èĥĤ
    0.26
    æľīèī²
    0.25
    :params
    0.25
    å·¨é¢Ŀ
    0.25
    Activations Density 2.514%

    No Known Activations