© 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. 25-TRANSCODER-HP
    7. 108226
    Prev
    Next
    INDEX
    Explanations

    Dates, numbers, and times

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     next
    -0.30
    -next
    -0.28
     dur
    -0.28
    éĺĶ
    -0.27
     NEXT
    -0.27
     +
    -0.26
    next
    -0.26
     thai
    -0.26
    èµ·
    -0.25
    å¾ĢåIJİ
    -0.25
    POSITIVE LOGITS
    prise
    0.25
    åįıä¼ļä¼ļåijĺ
    0.25
    åķĨæĬ¥
    0.24
    .Encode
    0.24
    smith
    0.24
    enames
    0.23
     Rahmen
    0.23
    nings
    0.23
    è´¬
    0.23
    IFEST
    0.23
    Activations Density 1.040%

    No Known Activations