© 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. 108597
    Prev
    Next
    INDEX
    Explanations

    Microsoft

    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
    roud
    -0.28
    olls
    -0.27
    è¿
    -0.26
    å²Ķ
    -0.26
    æł¼æŀĹ
    -0.25
    ãĤ¢ãĥĬ
    -0.25
    è¿Ĥ
    -0.25
    yntax
    -0.25
    ought
    -0.25
    为空
    -0.24
    POSITIVE LOGITS
    .persist
    0.28
    GC
    0.27
    DIRECT
    0.26
     RECT
    0.26
    gc
    0.25
     patented
    0.25
     Eugene
    0.25
     {{
    0.24
     resignation
    0.24
     itself
    0.23
    Activations Density 0.231%

    No Known Activations