© 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. 108605
    Prev
    Next
    INDEX
    Explanations

    2

    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
     glob
    -0.34
    åľ°çIJĥä¸Ĭ
    -0.33
    åħ¨çIJĥ
    -0.33
    åľ¨åħ¨çIJĥ
    -0.32
     mankind
    -0.32
    åľ°çIJĥ
    -0.32
     globe
    -0.31
    (Global
    -0.31
    ä¸ĸçķĮ
    -0.31
    人类
    -0.31
    POSITIVE LOGITS
     nationwide
    0.53
    åħ¨åĽ½
    0.48
    åħ¨åľĭ
    0.45
     national
    0.44
    ä¸ŃåĽ½çļĦ
    0.44
     nationally
    0.43
    åĽ½åĨħ
    0.42
     Nationwide
    0.40
    åľ¨åħ¨åĽ½
    0.40
    æĪijåĽ½
    0.38
    Activations Density 1.031%

    No Known Activations