© 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. 19-TRANSCODER-HP
    7. 6509
    Prev
    Next
    INDEX
    Explanations

    Years

    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
    mine
    -0.26
    æĿ¥æºIJäºİ
    -0.25
    mos
    -0.25
    irts
    -0.25
    å¿Į
    -0.25
    eger
    -0.25
    elter
    -0.24
     phiếu
    -0.24
    anne
    -0.24
    -rounded
    -0.24
    POSITIVE LOGITS
    æ´»
    0.28
    ifers
    0.27
    iu
    0.27
    Including
    0.26
    ä¿Ĺ
    0.26
    ä½Ĩè¿Ļ
    0.26
    ahead
    0.26
    ä¹Łä¸įä¾ĭå¤ĸ
    0.25
    forget
    0.25
    wx
    0.24
    Activations Density 0.811%

    No Known Activations