© 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. 33-TRANSCODER-HP
    7. 54322
    Prev
    Next
    INDEX
    Explanations

    grass

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rs
    -0.30
    票
    -0.29
    ker
    -0.28
    åŁº
    -0.28
    ÑĢай
    -0.27
    ariat
    -0.26
    åħ¬ç¤¾
    -0.26
    áºŃu
    -0.26
    èµĦ
    -0.26
    ertest
    -0.26
    POSITIVE LOGITS
    ogne
    0.29
     cann
    0.28
     cl
    0.27
    icl
    0.27
    æĮ¹
    0.26
    æ²
    0.25
     IDisposable
    0.25
    è±
    0.24
    tics
    0.24
    .Globalization
    0.24
    Activations Density 0.005%

    No Known Activations