© 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. 108228
    Prev
    Next
    INDEX
    Explanations

    Medical/Scientific texts

    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
    康å¤į
    -0.55
    åĮ»çĸĹ
    -0.50
     healing
    -0.49
    çĹĬ
    -0.49
    伤åı£
    -0.48
    çĸĹ
    -0.48
    çĹħæĥħ
    -0.47
    åį§
    -0.46
    ä½ıéĻ¢
    -0.46
     healed
    -0.45
    POSITIVE LOGITS
     diamonds
    0.26
    å¤ĸæĿ¥
    0.24
    ombok
    0.24
     Chess
    0.24
     tac
    0.23
     recycle
    0.23
     chess
    0.23
     recycled
    0.23
    iances
    0.23
     craft
    0.23
    Activations Density 3.737%

    No Known Activations