© 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. 19-TRANSCODER-HP
    7. 7944
    Prev
    Next
    INDEX
    Explanations

    from, through, at

    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
    æıIJä¾ĽæĽ´å¤ļ
    -0.31
    oky
    -0.27
    estic
    -0.27
    expectException
    -0.27
    IntArray
    -0.26
     UNU
    -0.26
     &↵
    -0.25
    yles
    -0.24
    çľĭä½ł
    -0.24
    zens
    -0.24
    POSITIVE LOGITS
     centrif
    0.28
    æĪIJçĨŁ
    0.27
     Language
    0.26
     accounts
    0.26
    è¯Ńè¨Ģ
    0.26
    å¸IJ
    0.25
     language
    0.25
    åı¦ä¸Ģæĸ¹éĿ¢
    0.25
     Magnus
    0.25
     centr
    0.25
    Activations Density 0.132%

    No Known Activations