© 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. 40052
    Prev
    Next
    INDEX
    Explanations

    Lizards

    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
    éĹ®æĪij
    -0.29
    uan
    -0.28
     Vor
    -0.28
    åŃ¦ä¹łè´¯å½»
    -0.27
    æıIJ示
    -0.27
    orage
    -0.25
    s
    -0.24
    æĦ¿
    -0.24
    -INF
    -0.24
    пÑĢав
    -0.24
    POSITIVE LOGITS
    prevState
    0.32
    CUS
    0.28
    ><![
    0.26
    ensus
    0.26
    DataGridViewTextBoxColumn
    0.26
    ç½¢
    0.25
    æĺĻ
    0.25
    ISCO
    0.25
     histories
    0.25
    isa
    0.24
    Activations Density 1.058%

    No Known Activations