© 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
    2. Qwen3-4B
    3. 19-TRANSCODER-HP
    4. 5046
    Prev
    Next
    INDEX
    Explanations

    Code snippets/technical documentation

    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
     neighbouring
    -0.26
    zes
    -0.25
    ertain
    -0.25
     neighbours
    -0.24
    -fetch
    -0.24
    *dt
    -0.24
    å¸Ń
    -0.24
    å®´ä¼ļ
    -0.24
    .EX
    -0.23
    驾
    -0.23
    POSITIVE LOGITS
     deprecated
    0.46
    ä¸įåĨį
    0.40
     Deprecated
    0.38
    ä¸įåĨįæĺ¯
    0.38
     replaced
    0.37
    ä¸įä¼ļåĨį
    0.36
    ä»Ĭãģ¯
    0.35
    æĹ¶ä»£
    0.35
    ä»Ĭ
    0.35
    çļĦæĹ¶ä»£
    0.35
    Activations Density 0.141%

    No Known Activations