© 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. 64092
    Prev
    Next
    INDEX
    Explanations

    Dates and numerical references

    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
    继ç»Ń
    -0.35
     continued
    -0.32
     continuing
    -0.31
    ç¹¼çºĮ
    -0.29
     Continued
    -0.28
     Continuing
    -0.28
    ä¸įåĨį
    -0.27
    ár
    -0.27
    çī¹æľĹ
    -0.26
    ttl
    -0.25
    POSITIVE LOGITS
    ahas
    0.27
    åıªæĺ¯ä¸Ģ个
    0.25
    ä¸į代表
    0.25
    æ·ĺ
    0.25
    没åħ³ç³»
    0.25
    ä¹ĺ
    0.25
    æĭ©
    0.24
    æĴ®
    0.24
     coincidence
    0.24
    åĴĶ
    0.24
    Activations Density 62.676%

    No Known Activations