© 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. 33-TRANSCODER-HP
    7. 54238
    Prev
    Next
    INDEX
    Explanations

    Code and URLs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ«ãģ¤
    -0.29
    伺
    -0.27
    å¹³éĿĻ
    -0.26
     uÄŁ
    -0.25
    AME
    -0.25
    æĹłäºº
    -0.25
    èµĬ
    -0.24
    these
    -0.24
    天ä¸ĭ
    -0.24
    è´Ł
    -0.24
    POSITIVE LOGITS
     Martins
    0.26
    -cart
    0.25
    atos
    0.25
    fir
    0.25
    ctic
    0.25
     UserManager
    0.25
    kiye
    0.25
    fi
    0.25
    еле
    0.24
     khá
    0.24
    Activations Density 0.011%

    No Known Activations