© 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. 63160
    Prev
    Next
    INDEX
    Explanations

    :

    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
    åİ®
    -0.28
    æŀ«
    -0.28
    没éĴ±
    -0.28
    没æľīå¿ħè¦ģ
    -0.27
    UTE
    -0.27
    åı¶åŃIJ
    -0.27
    çīĻ齿
    -0.25
    ute
    -0.25
    кÑĢи
    -0.25
    æĺµ
    -0.24
    POSITIVE LOGITS
    bnb
    0.25
    åįĬå²Ľ
    0.25
    æľįåĬ¡ä¸ļ
    0.25
    ernel
    0.24
    人士
    0.23
    åī
    0.23
    IES
    0.23
    åĨįå¤ļ
    0.23
    lld
    0.23
     method
    0.23
    Activations Density 4.830%

    No Known Activations