© 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. 41815
    Prev
    Next
    INDEX
    Explanations

    every

    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
     individuals
    -0.33
     animals
    -0.31
    entities
    -0.30
     manufacturers
    -0.28
     entities
    -0.28
    gers
    -0.28
    persons
    -0.28
    ographers
    -0.28
    -makers
    -0.27
     partners
    -0.27
    POSITIVE LOGITS
     learner
    0.37
    ä¸ĢåIJį
    0.36
    ä¸Ģä½į
    0.31
    .student
    0.30
     student
    0.30
    elper
    0.30
    åı¦ä¸Ģä½į
    0.29
    çļĦåѦçĶŁ
    0.28
    .createClass
    0.28
    CADE
    0.27
    Activations Density 0.000%

    No Known Activations