© 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. 96663
    Prev
    Next
    INDEX
    Explanations

    second

    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
    apl
    -0.27
    AndView
    -0.26
     Murray
    -0.25
    ichten
    -0.25
    EMA
    -0.25
    æ±ŁåĮĹ
    -0.24
    ftar
    -0.23
    rawer
    -0.23
    é»ijé¾Ļ
    -0.23
    idebar
    -0.23
    POSITIVE LOGITS
     second
    0.94
     sec
    0.89
    second
    0.87
    -second
    0.82
    ç§Ĵ
    0.78
    .second
    0.77
    第äºĮ
    0.77
    (second
    0.76
    Second
    0.76
     seconds
    0.76
    Activations Density 0.992%

    No Known Activations