© 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. 4976
    Prev
    Next
    INDEX
    Explanations

    cold

    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
    åı¯è¡ĮæĢ§
    -0.26
     lately
    -0.23
    ally
    -0.22
    ä¸Ģå®ļ
    -0.22
    vable
    -0.22
    -General
    -0.22
    æĸ¼
    -0.22
    overe
    -0.22
    antly
    -0.21
     hạ
    -0.21
    POSITIVE LOGITS
    noon
    0.27
    -hearted
    0.27
    ä½İè°ĥ
    0.26
    峡
    0.25
    -tone
    0.25
    -blood
    0.24
     tones
    0.24
    -headed
    0.23
    æĺ¶
    0.23
    dead
    0.22
    Activations Density 1.709%

    No Known Activations