© 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. 6888
    Prev
    Next
    INDEX
    Explanations

    organizations, government

    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
    ä»ĸåľ¨
    -0.29
     ÐŀÐŀ
    -0.28
    alem
    -0.27
    éĩįå¤į
    -0.27
    è¶ĬæĿ¥è¶Ĭå°ij
    -0.26
    éķĬ
    -0.26
    åī½
    -0.26
    æľī个
    -0.25
     dps
    -0.25
     Sunder
    -0.24
    POSITIVE LOGITS
    usta
    0.28
    Raised
    0.28
     #:
    0.27
    elled
    0.27
    rais
    0.27
    illed
    0.26
    dle
    0.26
    ÇĶ
    0.25
    nos
    0.25
    {:
    0.25
    Activations Density 0.025%

    No Known Activations