© 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. 63245
    Prev
    Next
    INDEX
    Explanations

    Interjections

    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
    Ĥ¨
    -0.30
    äºĨåIJ§
    -0.27
     embraced
    -0.26
    олов
    -0.25
    ElementException
    -0.25
    ç´łæĿIJ
    -0.24
    大人
    -0.24
     dấu
    -0.23
    ếc
    -0.23
    åĪ°åºķ
    -0.23
    POSITIVE LOGITS
    è¾¹
    0.28
     inter
    0.28
    çĶ¨æĪ·çļĦ
    0.27
    çģ¯çģ«
    0.25
    æĤ£èĢħçļĦ
    0.24
    ÎIJ
    0.24
     complex
    0.24
     MBA
    0.24
     te
    0.24
    å¤Ħå¤Ħ
    0.24
    Activations Density 15.233%

    No Known Activations