© 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. 40332
    Prev
    Next
    INDEX
    Explanations

    Code/technical text

    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
    tempts
    -0.27
     lạc
    -0.26
     lắp
    -0.25
     Pan
    -0.25
    (drop
    -0.25
    æ²Ł
    -0.24
    æ£Ģç´¢
    -0.24
    æĩĤ
    -0.24
    ounter
    -0.24
    åĽ¢ä½ĵ
    -0.24
    POSITIVE LOGITS
    /respond
    0.28
    èĪŁ
    0.27
    çļĦåİĭåĬĽ
    0.27
    绢
    0.27
    iona
    0.25
     usur
    0.25
     lem
    0.24
    -fe
    0.24
     Tomorrow
    0.24
    ortho
    0.24
    Activations Density 0.131%

    No Known Activations