© 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. 96201
    Prev
    Next
    INDEX
    Explanations

    variations of "introduce"

    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
    ferences
    -0.28
    onald
    -0.26
    åīĬå¼±
    -0.26
    lish
    -0.25
    æ¾Ħ
    -0.25
    éļıåį³
    -0.25
    åıij表äºĨ
    -0.24
     slashed
    -0.24
    ç»ĵæĿŁäºĨ
    -0.24
    èĤ©èĨĢ
    -0.24
    POSITIVE LOGITS
     introduction
    0.47
     introduced
    0.47
     introduce
    0.45
    å¼ķåħ¥
    0.44
     introduces
    0.41
    Introduction
    0.38
     Introduction
    0.37
     intro
    0.37
     introducing
    0.36
     introdu
    0.34
    Activations Density 0.884%

    No Known Activations