© 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. 18-TRANSCODER-HP
    7. 89369
    Prev
    Next
    INDEX
    Explanations

    Numbers and numerical operations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æīĵå¾Ĺ
    -0.29
    ).</
    -0.29
    too
    -0.28
    太太
    -0.27
    Subjects
    -0.27
     Äijá»Ŀi
    -0.27
    ãĢĤ</
    -0.26
    å¼¹
    -0.26
    Emp
    -0.26
    !).↵↵
    -0.26
    POSITIVE LOGITS
    ¶ļ
    0.29
    /native
    0.28
     nic
    0.27
    è¯Ŀ说
    0.27
    åĥ®
    0.26
    ä¸Ŀ绸ä¹ĭè·¯
    0.25
    /goto
    0.25
    -tone
    0.25
    è¦ģåİ»
    0.24
    ä¸¤åľ°
    0.24
    Activations Density 35.125%

    No Known Activations