© 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. 6209
    Prev
    Next
    INDEX
    Explanations

    Legal publication/filing

    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
    çķĻ
    -0.30
    åįģéĩĮ
    -0.27
    olis
    -0.25
     Tear
    -0.24
    .Sc
    -0.24
    Mov
    -0.24
     lightly
    -0.24
    ç»ĻæĪij们
    -0.24
    æµĴ
    -0.23
    çļĦç¨ĭ度
    -0.23
    POSITIVE LOGITS
    rim
    0.27
    allee
    0.27
    è§ģ解
    0.26
    tÃŃ
    0.25
    oral
    0.24
     comed
    0.24
    产åIJİ
    0.24
    æĹłè®ºå¦Ĥä½ķ
    0.24
     assim
    0.23
    鼳
    0.23
    Activations Density 0.023%

    No Known Activations