© 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. 32-TRANSCODER-HP
    7. 42812
    Prev
    Next
    INDEX
    Explanations

    Code and compression algorithms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åİĭ
    -0.32
    zas
    -0.29
    å£ĵ
    -0.29
     press
    -0.27
    ä¸įèĥ½ä¸ºç©º
    -0.27
     Zimmerman
    -0.27
    phas
    -0.26
    зо
    -0.26
    za
    -0.26
    Press
    -0.25
    POSITIVE LOGITS
    çļĦæķ°æį®
    0.28
    佩
    0.27
    /UI
    0.27
     undef
    0.27
    data
    0.27
    åī¯ä¸»ä»»
    0.27
     Data
    0.26
    éĺ²å¾¡
    0.26
    æķ°æį®
    0.25
     data
    0.25
    Activations Density 0.015%

    No Known Activations