© 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
    2. Qwen3-4B
    3. 27-TRANSCODER-HP
    4. 8452
    Prev
    Next
    INDEX
    Explanations

    Martin

    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
    neys
    -0.26
    uces
    -0.26
    $o
    -0.25
    èĵĸ
    -0.25
     campaign
    -0.25
    campaign
    -0.25
    lek
    -0.25
    quo
    -0.24
    aptured
    -0.24
    æ°©
    -0.24
    POSITIVE LOGITS
     equivalent
    0.32
    æĹłæĦı
    0.27
     Equivalent
    0.27
    主åĬ¨
    0.25
    ç²¾éĢī
    0.25
    fig
    0.25
     straw
    0.24
    ster
    0.24
    毡
    0.24
    代åĬŀ
    0.24
    Activations Density 0.003%

    No Known Activations