© 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. 14-TRANSCODER-HP
    7. 40494
    Prev
    Next
    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bill
    -0.25
    æ±ł
    -0.25
    ady
    -0.25
    æł·åĵģ
    -0.24
    ä¸į认è¯Ĩ
    -0.24
    ussy
    -0.24
    ngen
    -0.23
    æł·æľ¬
    -0.23
     sill
    -0.23
     pools
    -0.23
    POSITIVE LOGITS
    -unit
    0.27
     kos
    0.26
    eve
    0.26
    å¸ĥå°Ķ
    0.26
    REFER
    0.25
     bonuses
    0.25
    ev
    0.25
    .unit
    0.25
    é³IJ
    0.24
    unit
    0.24
    Activations Density 0.363%

    No Known Activations