© 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. 4719
    Prev
    Next
    INDEX
    Explanations

    Negation

    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
     Gast
    -0.31
     gast
    -0.31
     NDP
    -0.28
    insky
    -0.27
    ustria
    -0.26
    æķĻæĿIJ
    -0.25
    erge
    -0.25
    ụ
    -0.23
    çķĻåľ¨
    -0.23
    sWith
    -0.23
    POSITIVE LOGITS
    ippers
    0.28
    ãģ¡ãģª
    0.26
    cors
    0.24
    æīª
    0.24
    ensi
    0.24
    ä¸¤å¼ł
    0.24
     orth
    0.24
     purely
    0.24
    è°Į
    0.24
    fone
    0.24
    Activations Density 0.013%

    No Known Activations