© 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. 42223
    Prev
    Next
    INDEX
    Explanations

    top

    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
     top
    -0.29
    .top
    -0.27
    top
    -0.27
    á»ij
    -0.27
    ;top
    -0.26
     topo
    -0.26
    第ä¸ĢæĿ¡
    -0.26
    <table
    -0.26
     solely
    -0.25
    asurement
    -0.25
    POSITIVE LOGITS
     performing
    0.49
     Performing
    0.44
    Perform
    0.43
    perform
    0.43
     perform
    0.41
     Perform
    0.39
     performed
    0.39
     ten
    0.38
     performs
    0.38
     performers
    0.36
    Activations Density 0.008%

    No Known Activations