© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6533
    Prev
    Next
    INDEX
    Explanations

    right

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    失è°ĥ
    -0.27
    æĸ·
    -0.27
    vio
    -0.25
    æģĭæĥħ
    -0.25
    æĸŃ
    -0.25
    inction
    -0.25
    é¼»åŃIJ
    -0.23
    .histogram
    -0.23
    msp
    -0.23
     Capability
    -0.23
    POSITIVE LOGITS
     sized
    0.32
    -sized
    0.29
     kind
    0.28
    ITU
    0.26
     partition
    0.25
    ä¸ĭè¡Į
    0.25
    å½¢
    0.25
    kind
    0.25
    第
    0.25
    istr
    0.24
    Activations Density 0.088%

    No Known Activations