© 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. 6589
    Prev
    Next
    INDEX
    Explanations

    be

    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
    ãģĿãģĨãģ§ãģĻ
    -0.29
    æĹı
    -0.27
     alone
    -0.26
    uary
    -0.26
    anian
    -0.25
    riage
    -0.25
    æĽ°
    -0.24
    æĹ¥
    -0.24
    pets
    -0.24
    -legged
    -0.24
    POSITIVE LOGITS
    并ä¸İ
    0.30
    并åIJij
    0.29
    并äºİ
    0.27
    .opensource
    0.26
    è¾ĥ强
    0.25
    ä½łä¼ļåıijçİ°
    0.25
    ä¸Ńåħ³
    0.25
    ä½łåºĶ该
    0.24
    åħ¬åı¸å°Ĩ
    0.24
    并å°Ĩ
    0.24
    Activations Density 0.084%

    No Known Activations