© 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. 63119
    Prev
    Next
    INDEX
    Explanations

    Speech or communication

    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
    åŃIJ
    -0.30
    ian
    -0.28
    森
    -0.26
    ·
    -0.26
    çĹħ
    -0.26
     yourselves
    -0.25
    è®°å½ķ
    -0.25
    ä¹ŁåºĶ该
    -0.24
     sub
    -0.23
    elsen
    -0.23
    POSITIVE LOGITS
     pratique
    0.26
    actice
    0.24
     ká»ĭch
    0.24
    æĭĽåij¼
    0.24
    oning
    0.24
    /feed
    0.24
    æıIJè´¨
    0.24
    ãģĵãģĿ
    0.23
    ä¼ĺäºİ
    0.23
    è¿Ľä¿®
    0.23
    Activations Density 18.078%

    No Known Activations