© 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. 27-TRANSCODER-HP
    7. 9462
    Prev
    Next
    INDEX
    Explanations

    Code/disclaimers/announcements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hardware
    -1.14
    硬件
    -1.09
     Hardware
    -1.03
    Hardware
    -1.00
    hardware
    -0.94
    .hardware
    -0.82
    ardware
    -0.71
     devices
    -0.70
     device
    -0.67
    _hw
    -0.66
    POSITIVE LOGITS
    ockets
    0.35
    freeze
    0.27
    åĴ³åĹ½
    0.26
    iggins
    0.25
     scalar
    0.25
    æŃĮ声
    0.24
    ække
    0.23
    è´¼
    0.23
    åĨ°éĽª
    0.23
    asset
    0.23
    Activations Density 0.010%

    No Known Activations