© 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. 54290
    Prev
    Next
    INDEX
    Explanations

    .

    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
    layui
    -0.27
    odem
    -0.27
     Volt
    -0.26
    traî
    -0.26
    artin
    -0.26
    usty
    -0.25
    åı£åı·
    -0.25
    cfg
    -0.25
    ilot
    -0.25
    oy
    -0.25
    POSITIVE LOGITS
    waters
    0.27
    æĥ³èµ·æĿ¥
    0.27
    ornings
    0.27
    urses
    0.24
    ä¸ĢæĿ¡é¾Ļ
    0.24
    ×Ļ×Ķ
    0.23
    .leading
    0.23
    ipples
    0.23
    ferred
    0.23
     mor
    0.23
    Activations Density 0.003%

    No Known Activations