© 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. 130493
    Prev
    Next
    INDEX
    Explanations

    All

    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
    éĥ¨
    -0.28
    åīĸ
    -0.27
     bell
    -0.27
    calar
    -0.26
    è¾Ľ
    -0.26
    slick
    -0.25
    缴å±ŀ
    -0.25
    l
    -0.24
    æľĢåħ³éĶ®çļĦ
    -0.24
    nal
    -0.24
    POSITIVE LOGITS
    ParticleSystem
    0.25
    REAM
    0.25
    emsp
    0.25
    ä¸įèµ·
    0.25
    VOICE
    0.24
     pii
    0.23
    è¯ŃéŁ³
    0.23
    erculosis
    0.23
    票
    0.23
     Grammar
    0.23
    Activations Density 20.222%

    No Known Activations