© 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. 108256
    Prev
    Next
    INDEX
    Explanations

    ed

    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
     stabil
    -0.29
    /MPL
    -0.28
     complying
    -0.25
    ä¸įåIJĮæĦı
    -0.25
    æĤ¨åIJĮæĦı
    -0.24
     Nagar
    -0.24
    IOD
    -0.24
     conform
    -0.23
     phil
    -0.23
     Medina
    -0.23
    POSITIVE LOGITS
    armed
    0.26
    大家éĥ½åľ¨
    0.25
    TreeView
    0.25
    åī§éĻ¢
    0.24
    çĿ¹
    0.24
    criptions
    0.23
     Muss
    0.23
    çĿģå¼Ģ
    0.23
    fortune
    0.23
    odies
    0.23
    Activations Density 0.009%

    No Known Activations