© 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. 108077
    Prev
    Next
    INDEX
    Explanations

    technical, mechanical contexts

    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
    åĪ°è´¦
    -0.26
    èĥŀ
    -0.26
     ([[
    -0.25
    èĦĵ
    -0.24
    wat
    -0.24
    ç»İ
    -0.24
     uÄŁ
    -0.24
     nto
    -0.23
    Wat
    -0.23
    æį®æѤ
    -0.23
    POSITIVE LOGITS
     testing
    0.31
     installation
    0.30
     tests
    0.29
     disposal
    0.28
    ä»Ģä¹Īäºĭæĥħ
    0.28
     Sahara
    0.28
    eties
    0.27
     test
    0.27
     testName
    0.27
    ities
    0.26
    Activations Density 1.066%

    No Known Activations