© 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. 6971
    Prev
    Next
    INDEX
    Explanations

    change or new developments

    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
    æĸ°çļĦ
    -0.48
    åıĺå¾ĹæĽ´åĬł
    -0.42
     redesigned
    -0.42
    åıĺå¾ĹæĽ´
    -0.42
    ä¸įåĨį
    -0.41
     improved
    -0.40
     revamped
    -0.39
    ä¸įåĨįæĺ¯
    -0.39
     newfound
    -0.38
    æĽ´åĬł
    -0.37
    POSITIVE LOGITS
     lifelong
    0.27
    tableFuture
    0.27
     incons
    0.27
    åĩºçĶŁ
    0.26
    æĭĴ
    0.26
    attended
    0.26
     Lif
    0.25
    å¥ĩèij©
    0.25
    _calibration
    0.24
    _FUN
    0.24
    Activations Density 0.072%

    No Known Activations