© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 107669
    Prev
    Next
    INDEX
    Explanations

    Mixed data types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    everything
    -0.28
    grounds
    -0.28
     fort
    -0.27
    _HANDLE
    -0.26
    iske
    -0.25
    ,[],
    -0.25
    å¹³åĿĩæ¯ı
    -0.24
    ersistence
    -0.24
     anything
    -0.24
    atings
    -0.23
    POSITIVE LOGITS
    ä¸įåĪĨ
    0.31
    缸åıį
    0.29
    åĬłä»¥
    0.28
    éĩĩçĶ¨
    0.27
    é¼ĵ
    0.26
    é¢Ŀå¤ĸ
    0.26
    åıįè¿ĩæĿ¥
    0.26
    éĤĿ
    0.26
    绣ä¸Ģ
    0.25
    _broadcast
    0.24
    Activations Density 1.440%

    No Known Activations