© 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. 30-TRANSCODER-HP
    7. 95783
    Prev
    Next
    INDEX
    Explanations

    variations of "lie"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è·¡
    -0.27
    åIJİéĿ¢çļĦ
    -0.26
    Suffix
    -0.26
    迹
    -0.25
     trailing
    -0.25
    itti
    -0.25
    ä¸Ģè½®
    -0.24
    ç»ĵå°¾
    -0.24
    FromArray
    -0.24
     hood
    -0.24
    POSITIVE LOGITS
     lie
    0.43
     lies
    0.42
     lying
    0.39
     Lie
    0.33
    lie
    0.33
     Lies
    0.33
    Lie
    0.33
     stretching
    0.30
    stretch
    0.29
     away
    0.29
    Activations Density 0.008%

    No Known Activations