© 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. 63675
    Prev
    Next
    INDEX
    Explanations

    Different usages of "as"

    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
    æľĪä¸ĭ
    -0.34
    æŀķ
    -0.31
    ropy
    -0.30
    umpt
    -0.28
    åĺ´
    -0.27
    èİĵ
    -0.26
    èĩªç§°
    -0.26
    appe
    -0.26
    éĿ¢ä¸Ĭ
    -0.25
    æĢ§å¼º
    -0.25
    POSITIVE LOGITS
     hers
    0.28
    æľīå¿ħè¦ģ
    0.28
    edException
    0.27
    ä¾µçĬ¯
    0.27
     conclus
    0.26
    åĶ¯æľī
    0.25
     throwable
    0.25
    DataTask
    0.24
    é¦Ļèķī
    0.24
    hazi
    0.23
    Activations Density 84.391%

    No Known Activations