© 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. 6179
    Prev
    Next
    INDEX
    Explanations

    or

    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
    utos
    -0.25
     Families
    -0.23
    lung
    -0.23
    稳å®ļçļĦ
    -0.23
    âĢ¦↵↵↵↵
    -0.23
    ENTA
    -0.23
    vida
    -0.22
    ayo
    -0.22
    **č↵
    -0.22
     quarter
    -0.22
    POSITIVE LOGITS
     bure
    0.29
    åŃIJéĩĮ
    0.25
     embryo
    0.25
    æīĴ
    0.24
    rogen
    0.24
     redraw
    0.24
    移
    0.24
    æŀª
    0.24
     biopsy
    0.24
    缺
    0.24
    Activations Density 0.052%

    No Known Activations