© 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. 31-TRANSCODER-HP
    7. 18259
    Prev
    Next
    INDEX
    Explanations

    yet

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    |č↵
    -0.25
     intermedi
    -0.25
    æļĤ
    -0.24
     flotation
    -0.24
     extr
    -0.24
     systematic
    -0.24
     (č↵
    -0.24
     systematically
    -0.23
    {č↵
    -0.23
    missions
    -0.23
    POSITIVE LOGITS
     now
    0.41
    -now
    0.37
    now
    0.37
    è¿Ļä¸Ģ次
    0.35
    .now
    0.34
    çİ°åľ¨
    0.33
     ahora
    0.33
     Now
    0.33
    	now
    0.33
    Now
    0.32
    Activations Density 0.024%

    No Known Activations