© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7127
    Prev
    Next
    INDEX
    Explanations

    Ian

    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
    çļĦçģµéŃĤ
    -0.30
    !]
    -0.27
    ĺ认
    -0.27
    æŶéĻIJ
    -0.26
    obl
    -0.24
    æĶ¾è¿Ľ
    -0.24
    аÑĪ
    -0.24
    ÑĢÑı
    -0.24
    ä¼ļéķ¿
    -0.24
    æĭ¿åĩºæĿ¥
    -0.24
    POSITIVE LOGITS
     net
    0.31
    un
    0.26
    æģ¯
    0.26
    _net
    0.26
    d
    0.26
     foot
    0.25
    ter
    0.25
     Unters
    0.24
    Un
    0.24
    net
    0.24
    Activations Density 0.032%

    No Known Activations