© 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. 25-TRANSCODER-HP
    7. 108672
    Prev
    Next
    INDEX
    Explanations

    medical research papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     simulation
    -0.43
    模æĭŁ
    -0.41
    simulation
    -0.39
     simulate
    -0.38
    模åŀĭ
    -0.38
     Simulation
    -0.36
     simulations
    -0.35
    ä»¿çľŁ
    -0.35
     sim
    -0.34
    Simulation
    -0.34
    POSITIVE LOGITS
    @stop
    0.26
     ÑĢождениÑı
    0.24
     spree
    0.24
    _setopt
    0.24
    .unlock
    0.24
    appa
    0.24
    _rand
    0.24
    _learning
    0.23
    gmail
    0.23
     Victory
    0.23
    Activations Density 1.271%

    No Known Activations