© 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. 141234
    Prev
    Next
    INDEX
    Explanations

    formal language

    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
     pull
    -0.28
    rade
    -0.27
     mass
    -0.27
    -depth
    -0.26
    æĬĦ
    -0.26
    æ¶ħ
    -0.26
    kr
    -0.25
    ole
    -0.25
    ç«Ļåľ¨
    -0.25
     bounced
    -0.24
    POSITIVE LOGITS
    ï¼ĮåĪĻ
    0.31
        ↵    ↵
    0.27
    Directive
    0.26
    ]*(
    0.26
    åĪĻæĺ¯
    0.26
    èĢĮè¨Ģ
    0.25
    uition
    0.25
    ä¿Ĥ
    0.25
     ones
    0.25
    dÃŃ
    0.25
    Activations Density 50.941%

    No Known Activations