© 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. 42031
    Prev
    Next
    INDEX
    Explanations

    inclusion

    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
    abeth
    -0.26
    rons
    -0.26
     bạc
    -0.26
    æĪĺ
    -0.25
    airy
    -0.25
    achen
    -0.24
    DEST
    -0.24
    PROP
    -0.24
    iron
    -0.24
     tabIndex
    -0.24
    POSITIVE LOGITS
     inclusion
    1.08
     included
    0.80
     include
    0.79
     inclus
    0.76
    included
    0.75
    åĮħåIJ«
    0.73
     Include
    0.73
     includes
    0.73
    Include
    0.72
     Included
    0.72
    Activations Density 0.000%

    No Known Activations