© 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. 108338
    Prev
    Next
    INDEX
    Explanations

    Upon

    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
    ly
    -0.27
    <'
    -0.24
    ãĤº
    -0.24
    çİ°
    -0.24
    éĤ£è¾¹
    -0.24
    Opens
    -0.24
    åĢŁéī´
    -0.24
    å¯Ħ
    -0.24
    ä¹ĭ
    -0.23
    åľ¨æĦı
    -0.23
    POSITIVE LOGITS
    ../../../
    0.30
    ái
    0.28
    azer
    0.27
    ardin
    0.26
    ogene
    0.24
    å¾Ĺåĩº
    0.24
    uiten
    0.24
    æĭ¿åĩº
    0.24
    åѦçĶŁçļĦ
    0.24
    被è¯Ħ为
    0.24
    Activations Density 0.068%

    No Known Activations